# ModelScale > Source-aware model, pricing and workload evidence for practical AI decisions, published by MonoMind AI Lab. ModelScale reproduces what upstream sources publish about large language models. No published figure is modelled, estimated or interpolated; the cost simulator's estimates are labelled as estimates and built only from published token rates and the workload a reader enters. Each model carries 7 capability axes (Agentic, Coding, Knowledge, Reasoning, Multimodal & Grounded, Instruction Following, Math), list token prices per million tokens, measured time to first token and output throughput, a context window and a release date. The upstream projects are BenchLM, LiveBench and OpenRouter; models.dev (MIT License) fills gaps they leave, and Vercel AI Gateway's listing is used for cross-checking prices only, never as the source of a value. Model profiles also show independent benchmark scores from Epoch AI (CC BY 4.0, https://epoch.ai/benchmarks), kept apart from the capability scores and rank. Every fetch is dated, and the date is shown beside the value rather than behind it. Each value carries an evidence status. `observed` means a source published it on the date shown. `retained` means the last good reading is being shown because the newest fetch did not carry that field. `unavailable` means no source publishes it, and `failed` means the fetch itself did not succeed. The last two render as a missing value — never a zero, never an invented number. Where a line in this file omits a figure, that is why. ## Pages - [ModelScale — evidence for AI runtime and cost decisions](https://modelscale.dev/): Compare AI model capability, runtime and price against the sources each figure came from. A measurement nobody published stays unavailable, never a zero. - [Models workbench](https://modelscale.dev/models): Filter the model catalog by provider, access and capability, read the price-performance frontier, and carry two to four models into a shareable comparison. - [Popular models leaderboard](https://modelscale.dev/popular-models): Rank models across seven capability axes with sortable columns, per-model benchmark rows and quality-against-cost plots. Export the table as CSV or PNG. - [Leaderboards](https://modelscale.dev/leaderboards): Every ranking on ModelScale: the whole catalog, the seven capability axes, and one leaderboard for each benchmark the sources publish a value for. - [Agentic models leaderboard](https://modelscale.dev/leaderboards/agentic): Rank every model by its agentic capability score — planning, tool use and multi-step task completion — with overall score, blended cost and evidence links. - [Coding models leaderboard](https://modelscale.dev/leaderboards/coding): Rank every model by its coding capability score — writing, debugging and reasoning about code — with overall score, blended cost and evidence links. - [Knowledge models leaderboard](https://modelscale.dev/leaderboards/knowledge): Rank every model by its knowledge capability score — breadth and accuracy of factual recall — with overall score, blended cost and evidence links. - [Reasoning models leaderboard](https://modelscale.dev/leaderboards/reasoning): Rank every model by its reasoning capability score — multi-step logical and analytical problem-solving — with overall score, blended cost and evidence links. - [Multimodal models leaderboard](https://modelscale.dev/leaderboards/multimodal): Rank every model by its multimodal score — reading images, charts and documents — with overall score, blended cost and evidence links. - [Instruction following models leaderboard](https://modelscale.dev/leaderboards/instruction-following): Rank every model by its instruction following score — doing exactly what a prompt asks — with overall score, blended cost and evidence links. - [Math models leaderboard](https://modelscale.dev/leaderboards/math): Rank every model by its math capability score — competition problems and multi-step calculation — with overall score, blended cost and evidence links. - [Compare models](https://modelscale.dev/compare): Put two to four models side by side: capability scores, runtime measurements, every published price component, and the pair deltas the source itself computed. - [Compare by Provider](https://modelscale.dev/compare/providers): Rank every model from two to four providers together on one capability table and one quality-against-cost plot, with the source behind every figure. - [Make it yours](https://modelscale.dev/make-it-yours): Weight the seven capability axes and throughput, set runtime thresholds, and rank every model by the weighted sum of the scores its sources actually measured. - [Cost simulator: how much will it cost?](https://modelscale.dev/subscribe-vs-api): Estimate the monthly API cost of a workload from published token rates, itemised line by line, and compare it with a subscription plan if you like. - [How we estimate workloads](https://modelscale.dev/how-we-estimate-workloads): The planning figures the cost simulator uses to turn people, chats and task sizes into tokens: our assumptions, never source evidence. - [Model lifecycle radar](https://modelscale.dev/model-lifecycle): Announced and observed model retirements with the source that published each date, the replacement each provider named, and how long is left before it lands. - [Articles](https://modelscale.dev/articles): Guides and analysis on model routing, usage monitoring and cost control, written against the same evidence rules as every figure elsewhere on the site. - [Cited sources](https://modelscale.dev/sources): Every upstream fetch behind the site, the full benchmark catalog grouped by category, and the rules that govern how a value is shown and cited. Every benchmark in the catalog also has a leaderboard of its own at `/leaderboards/benchmarks/{benchmark}`. There are several hundred, so rather than spend this file's budget enumerating them, the 6 the site features are listed below; https://modelscale.dev/leaderboards indexes all of them by category and https://modelscale.dev/sitemap.xml carries every URL. - [SWE-bench Verified leaderboard](https://modelscale.dev/leaderboards/benchmarks/coding-swe-verified): SWE-bench Verified tests patches for 500 human-filtered GitHub issues. - [Terminal-Bench 2.0 leaderboard](https://modelscale.dev/leaderboards/benchmarks/agentic-terminal-bench2): A benchmark for agentic software engineering tasks executed in real terminal environments. - [GPQA-D leaderboard](https://modelscale.dev/leaderboards/benchmarks/knowledge-gpqa-diamond): Graduate-level science questions from provider comparison charts and open evaluations. - [FrontierMath v2 (Tiers 1-3) leaderboard](https://modelscale.dev/leaderboards/benchmarks/math-frontier-math-v2-tiers13): Epoch AI's corrected v2 core FrontierMath suite of private advanced mathematics problems. - [MMMU-Pro leaderboard](https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-mmmu-pro): A harder multimodal benchmark for frontier models that combines text with images, diagrams, charts, and academic visual reasoning tasks. - [ARC-AGI-2 leaderboard](https://modelscale.dev/leaderboards/benchmarks/reasoning-arc-agi2): ARC-AGI-2 tests whether a system can infer a transformation from example grids and apply it to a new grid. Both comparison pages take a selection in the query string and canonicalise it to one URL per selection. These are the comparisons the site currently features, in that canonical form: - [Claude Fable 5.2 vs GPT-6.2 Astra](https://modelscale.dev/compare/claude-fable-5-2-vs-gpt-6-2-astra): The catalog's two highest-ranked models, head to head on every capability axis. - [Gemini 4 Carbon vs GPT-6 Astra](https://modelscale.dev/compare/gemini-4-carbon-vs-gpt-6-astra): The next two models in the published ranking from different providers, one rung below the leaders. - [Qwen3.7 Flash vs GPT-OSS 20B](https://modelscale.dev/compare/qwen3-7-flash-vs-gpt-oss-20b): The two lowest-priced models holding a place on the published price-performance frontier. - [Claude Fable 5.2 vs Kimi K3.1 Pro](https://modelscale.dev/compare/claude-fable-5-2-vs-kimi-3-1-pro): The highest-ranked open-weight model against the highest-ranked proprietary one. - [Claude Fable 5.2 vs GPT-OSS 20B](https://modelscale.dev/compare/claude-fable-5-2-vs-gpt-oss-20b): The top of the published ranking against the cheapest model still on the price-performance frontier. - [OpenAI vs Anthropic](https://modelscale.dev/compare/providers/openai-vs-anthropic): The two providers holding the highest-scoring models in the catalog, across their whole published ranges. - [Google vs Meta](https://modelscale.dev/compare/providers/google-vs-meta): The next two providers by their best published score, one tier below the leaders. - [OpenAI vs Alibaba](https://modelscale.dev/compare/providers/openai-vs-alibaba): The two largest scored ranges in the catalog, every model of each on one table. - [Anthropic vs Moonshot AI](https://modelscale.dev/compare/providers/anthropic-vs-moonshot-ai): The highest-scoring open-weight provider against the highest-scoring proprietary one. - [DeepSeek vs Moonshot AI vs Tencent](https://modelscale.dev/compare/providers/deepseek-vs-moonshot-ai-vs-tencent): The three highest-scoring open-weight providers at once, on one capability table and one plot. ## API One JSON endpoint is public on this domain: - [GET /api/model/{id}](https://modelscale.dev/api/model/claude-fable-5-1): One model's full evidence record, the same shape the profile page renders. The catalog API behind every page is reached over an internal service binding and has no published address on this domain, so its read paths are named here rather than linked: - `GET /api/v1/catalog` — Every model with its full evidence record: capability scores, prices, runtime measurements, and the source and date behind each value. - `GET /api/v1/catalog?view=summary` — The same catalog projected down to what a list needs. Every page that renders many models at once reads this rather than the full record, and it is the one to prefer unless you need per-benchmark detail. - `GET /api/v1/models/{id}` — One model's profile: benchmark task rows, source links, and lifecycle history. - `GET /api/v1/compare?models={ids}` — Pairwise category deltas for two to four comma-separated model ids, as the source published them rather than derived here. - `GET /api/v1/plans` — Published subscription plans with their charge, cadence, and the page each price was read from. - `GET /api/v1/lifecycle` — Release and retirement notices with announced and effective dates, and a replacement id where the provider named one. - `GET /api/v1/articles` — The editorial records behind /articles, as structured sections and blocks. ## Models - [Claude Fable 5.2 (Anthropic) — 93.2](https://modelscale.dev/models/claude-fable-5-2) - [GPT-6.2 Astra (OpenAI) — 91](https://modelscale.dev/models/gpt-6-2-astra) - [Gemini 4 Carbon (Google) — 88](https://modelscale.dev/models/gemini-4-carbon) - [Gemini 4 Neon (Google) — 86.3](https://modelscale.dev/models/gemini-4-neon) - [GPT-6 Astra (OpenAI) — 83.2](https://modelscale.dev/models/gpt-6-astra) - [Claude Opus 5.5 (Anthropic) — 82.7](https://modelscale.dev/models/claude-opus-5-5) - [GPT-6.2 Sol (OpenAI) — 82.6](https://modelscale.dev/models/gpt-6-2-sol) - [GPT-6.1 Sol (OpenAI) — 80.7](https://modelscale.dev/models/gpt-6-1-sol) - [GPT-6.1 Terra (OpenAI) — 80.4](https://modelscale.dev/models/gpt-6-1-terra) - [Gemini 4 Argon (Google) — 79.1](https://modelscale.dev/models/gemini-4-argon) - [Gemini 4 Hydrogen (Google) — 78.8](https://modelscale.dev/models/gemini-4-hydrogen) - [Claude Fable 5.1 (Anthropic) — 78.6](https://modelscale.dev/models/claude-fable-5-1) - [Claude Sonnet 5.5 (Anthropic) — 77.9](https://modelscale.dev/models/claude-sonnet-5-5) - [Muse Wonder Full (Meta) — 77.2](https://modelscale.dev/models/muse-wonder-full) - [Claude Opus 5 (Anthropic) — 74.9](https://modelscale.dev/models/claude-opus-5) - [Claude Fable 5 (Anthropic) — 74.6](https://modelscale.dev/models/claude-fable-5) - [Qwen4 Max (Alibaba) — 74.5](https://modelscale.dev/models/qwen4-max) - [GPT-6 Sol (OpenAI) — 73.3](https://modelscale.dev/models/gpt-6-sol) - [GPT-5.6 Sol (OpenAI) — 73](https://modelscale.dev/models/gpt-5-6-sol) - [Muse Wonder (Meta) — 71.1](https://modelscale.dev/models/muse-wonder) - [Kimi K3.1 Pro (Moonshot AI) — 70.6](https://modelscale.dev/models/kimi-3-1-pro) - [GPT-5.5 Pro (OpenAI) — 70.1](https://modelscale.dev/models/gpt-5-5-pro) - [DeepSeek V4.1 Flash 1017 (DeepSeek) — 70](https://modelscale.dev/models/deepseek-v4-1-flash) - [GPT-5.5 (OpenAI) — 69](https://modelscale.dev/models/gpt-5-5) - [Hy4 (Tencent) — 68.6](https://modelscale.dev/models/hy4) - [Hy4 preview (Tencent) — 68.3](https://modelscale.dev/models/hy4-preview) - [GPT-5.4 Pro (OpenAI) — 68.3](https://modelscale.dev/models/gpt-5-4-pro) - [MiniMax M3.1 Flash (MiniMax) — 68.1](https://modelscale.dev/models/minimax-m3-1-flash) - [Gemini 3.8 Flash (Google) — 67.7](https://modelscale.dev/models/gemini-3-8-flash) - [Ling 3.1 Flash (InclusionAI) — 66.8](https://modelscale.dev/models/ling-3-1-flash) - [Inkling 2 Small (Thinking Machines Lab) — 66.7](https://modelscale.dev/models/inkling-2-small) - [Claude Opus 4.8 (Anthropic) — 66.6](https://modelscale.dev/models/claude-opus-4-8) - [Gemini 3.7 Flash (Google) — 66.4](https://modelscale.dev/models/gemini-3-7-flash) - [GPT-5.6 Terra (OpenAI) — 65.9](https://modelscale.dev/models/gpt-5-6-terra) - [Claude Opus 4.7 (Adaptive) (Anthropic) — 65.75](https://modelscale.dev/models/claude-opus-4-7-max) - [Qwen3.8 Max (Alibaba) — 65.6](https://modelscale.dev/models/qwen3-8-max) - [Kimi K3 (Moonshot AI) — 65.5](https://modelscale.dev/models/kimi-3) - [Grok 4.6 (xAI) — 65.1](https://modelscale.dev/models/grok-4-6) - [GLM-5.3 (Z.AI) — 63.7](https://modelscale.dev/models/glm-5-3) - [Claude Haiku 5.5 (Anthropic) — 63.6](https://modelscale.dev/models/claude-haiku-5-5) - [MiMo-V2.6-Pro (Xiaomi) — 63.5](https://modelscale.dev/models/mimo-v2-6-pro) - [GPT-5.2 Pro (OpenAI) — 63.3](https://modelscale.dev/models/gpt-5-2-pro) - [Claude Opus 4.7 (Anthropic) — 63.2](https://modelscale.dev/models/claude-opus-4-7) - [MiMo-V2.6-Flash (Xiaomi) — 63.2](https://modelscale.dev/models/mimo-v2-6-flash) - [Ornith-1.5-397B (Ornith AI) — 63.2](https://modelscale.dev/models/ornith-1-5-397b) - [Step 5 Preview (StepFun) — 62.8](https://modelscale.dev/models/step-5-preview) - [GPT-5.4 (OpenAI) — 62.7](https://modelscale.dev/models/gpt-5-4) - [Claude Sonnet 5 (Anthropic) — 61.6](https://modelscale.dev/models/claude-sonnet-5) - [DeepSeek V4 Pro (DeepSeek) — 61.5](https://modelscale.dev/models/deepseek-v4-pro) - [GPT-6 Luna (OpenAI) — 61.3](https://modelscale.dev/models/gpt-6-luna) - [Gemini 3.1 Pro (Google) — 61](https://modelscale.dev/models/gemini-3-1-pro) - [Muse Ember (Meta) — 60.9](https://modelscale.dev/models/muse-ember) - [Qwen3.8-Flash-Next (Alibaba) — 60.8](https://modelscale.dev/models/qwen3-8-flash-next) - [Gemini 3.6 Flash (Google) — 60.4](https://modelscale.dev/models/gemini-3-6-flash) - [DeepSeek V4 Pro 0813 (DeepSeek) — 62.13](https://modelscale.dev/models/deepseek-v4-pro-max) - [Grok 4.5 (xAI) — 60.4](https://modelscale.dev/models/grok-4-5) - [GPT-5.6 Luna (OpenAI) — 60.2](https://modelscale.dev/models/gpt-5-6-luna) - [GPT-5.2 (OpenAI) — 60.1](https://modelscale.dev/models/gpt-5-2) - [dots3-note Preview (Dots Studio) — 59.9](https://modelscale.dev/models/dots3-note-preview) - [Muse Spark 1.2 (Meta) — 59.8](https://modelscale.dev/models/muse-spark-1-2) - [Gemini 3 Pro (Google) — 59.8](https://modelscale.dev/models/gemini-3-pro) - [Claude Opus 4.6 (Anthropic) — 59.8](https://modelscale.dev/models/claude-opus-4-6) - [Claude Opus 4.6 (Adaptive) (Anthropic) — 59.8](https://modelscale.dev/models/claude-opus-4-6-thinking) - [Gemini 3.5 Flash (Google) — 59.7](https://modelscale.dev/models/gemini-3-5-flash) - [Muse Spark 1.1 (Meta) — 59.5](https://modelscale.dev/models/muse-spark-1-1) - [Qwen3.8-Omni-Flash (Alibaba) — 59.5](https://modelscale.dev/models/qwen3-8-omni-flash) - [Gemini 3 Pro Deep Think (Google) — 59.81](https://modelscale.dev/models/gemini-3-pro-deep-think) - [GLM-5.2 (Z.AI) — 59.2](https://modelscale.dev/models/glm-5-2) - [Qwen3.7 Max (Alibaba) — 59](https://modelscale.dev/models/qwen3-7-max) - [GLM-5.3-Flash (Z.AI) — 58.3](https://modelscale.dev/models/glm-5-3-flash) - [Mistral Large 4 (Mistral) — 56.8](https://modelscale.dev/models/mistral-large-4) - [Inkling 2 Mini (Thinking Machines Lab) — 56](https://modelscale.dev/models/inkling-2-mini) - [Grok 4.1 (xAI) — 58.48](https://modelscale.dev/models/grok-4-1) - [Kimi K2.5 (Reasoning) (Moonshot AI) — 56.53](https://modelscale.dev/models/kimi-k2-5-reasoning) - [Muse Spark Open (Meta) — 55.8](https://modelscale.dev/models/muse-spark-open) - [GLM-5 (Reasoning) (Z.AI) — 58.3](https://modelscale.dev/models/glm-5-reasoning) - [MiMo-V2.5-Pro (Xiaomi) — 55.8](https://modelscale.dev/models/mimo-v2-5-pro) - [Qwen3.5 397B (Reasoning) (Alibaba) — 58.03](https://modelscale.dev/models/qwen3-5-397b-reasoning) - [Sage-A1.5 (InternScience) — 55.4](https://modelscale.dev/models/sage-a1-5) - [Agents-A1 (InternScience) — 54.37](https://modelscale.dev/models/agents-a1) - [o3 (OpenAI) — 55.3](https://modelscale.dev/models/o3) - [Agents-A1-F16-GGUF (InternScience) — 54.37](https://modelscale.dev/models/agents-a1-f16-gguf) - [Qwen3.8-27B (Alibaba) — 55](https://modelscale.dev/models/qwen3-8-27b) - [Agents-A1-FP8 (InternScience) — 54.37](https://modelscale.dev/models/agents-a1-fp8) - [GPT-5.3 Codex (OpenAI) — 54.9](https://modelscale.dev/models/gpt-5-3-codex) - [Agents-A1-Q4_K_M-GGUF (InternScience) — 54.37](https://modelscale.dev/models/agents-a1-q4-k-m-gguf) - [Apodex 1.1 (Apodex) — 54.8](https://modelscale.dev/models/apodex-1-1) - [Agents-A1-Q8_0-GGUF (InternScience) — 54.37](https://modelscale.dev/models/agents-a1-q8-0-gguf) - [GPT-5.2 Instant (OpenAI) — 57.55](https://modelscale.dev/models/gpt-5-2-instant) - [Qwen3.7 Plus (Alibaba) — 54.5](https://modelscale.dev/models/qwen3-7-plus) - [Claude Opus 4.5 (Anthropic) — 54.4](https://modelscale.dev/models/claude-opus-4-5) - [GPT-5.3 Instant (OpenAI) — 57.44](https://modelscale.dev/models/gpt-5-3-instant) - [Claude Opus 4.5 Thinking (Anthropic) — 54.4](https://modelscale.dev/models/claude-opus-4-5-thinking) - [Kimi K2.6 (Moonshot AI) — 54.2](https://modelscale.dev/models/kimi-2-6) - [GPT-5 (OpenAI) — 54.1](https://modelscale.dev/models/gpt-5) - [GPT-5 (high) (OpenAI) — 57.19](https://modelscale.dev/models/gpt-5-high) - [Claude Sonnet 4.6 (Anthropic) — 53.8](https://modelscale.dev/models/claude-sonnet-4-6) - [Muse Spark (Meta) — 53.6](https://modelscale.dev/models/muse-spark) - [DeepSeek V3.2 (Thinking) (DeepSeek) — 56.68](https://modelscale.dev/models/deepseek-v3-2-thinking) - [Qwen 3.6 Max (preview) (Alibaba) — 53.2](https://modelscale.dev/models/qwen3-6-max-preview) - [Qwen3 235B 2507 (Reasoning) (Alibaba) — 56.57](https://modelscale.dev/models/qwen3-235b-2507-reasoning) - [Gemini 3 Flash (Google) — 53.1](https://modelscale.dev/models/gemini-3-flash) - [MiniMax M3 (MiniMax) — 52.6](https://modelscale.dev/models/minimax-m3) - [Kimi K2.7 Code (Moonshot AI) — 52.2](https://modelscale.dev/models/kimi-k2-7-code) - [MAI-Thinking-1 (Microsoft) — 52.91](https://modelscale.dev/models/mai-thinking-1) - [GLM-5.1 (Z.AI) — 52.2](https://modelscale.dev/models/glm-5-1) - [Hy3 (Tencent) — 52.1](https://modelscale.dev/models/hy3) - [GPT-5.3-Codex-Spark (OpenAI) — 55.49](https://modelscale.dev/models/gpt-5-3-codex-spark) - [Grok 4.20 (xAI) — 51.6](https://modelscale.dev/models/grok-4-20-beta) - [GPT-5.2-Codex (OpenAI) — 50.7](https://modelscale.dev/models/gpt-5-2-codex) - [o3-pro (OpenAI) — 50.4](https://modelscale.dev/models/o3-pro) - [GPT-5.4 mini (OpenAI) — 50.4](https://modelscale.dev/models/gpt-5-4-mini) - [Qwen3.6 Plus (Alibaba) — 50.2](https://modelscale.dev/models/qwen3-6-plus) - [MiMo-V2.5 (Xiaomi) — 50.1](https://modelscale.dev/models/mimo-v2-5) - [Quasar 438B (Multiverse Computing) — 49.12](https://modelscale.dev/models/quasar-438b) - [Gemini 3.5 Flash-Lite (Google) — 50.1](https://modelscale.dev/models/gemini-3-5-flash-lite) - [Nemotron 3 Ultra (NVIDIA) — 49.5](https://modelscale.dev/models/nemotron-3-ultra-500b) - [GPT-5.1 (OpenAI) — 49.2](https://modelscale.dev/models/gpt-5-1) - [Trinity-Large-Preview (Arcee AI) — 54.53](https://modelscale.dev/models/trinity-large-preview) - [Inkling (Thinking Machines Lab) — 48.9](https://modelscale.dev/models/inkling) - [Inkling-Small (Thinking Machines Lab) — 48.9](https://modelscale.dev/models/inkling-small) - [Ornith-1.5-35B-A3B (Ornith AI) — 48.8](https://modelscale.dev/models/ornith-1-5-35b-a3b) - [Grok 4 (xAI) — 48.1](https://modelscale.dev/models/grok-4) - [Ling 3.0 Flash (InclusionAI) — 48.1](https://modelscale.dev/models/ling-3-0-flash) - [Step 3.7 Flash (StepFun) — 48](https://modelscale.dev/models/step-3-7-flash) - [DeepSeek LLM 2.0 (DeepSeek) — 53.14](https://modelscale.dev/models/deepseek-llm-2-0) - [Ling 2.6 Flash (InclusionAI) — 47.8](https://modelscale.dev/models/ling-2-6-flash) - [Step 3.5 Flash (StepFun) — 47.7](https://modelscale.dev/models/step-3-5-flash) - [Beam 1.0 501B-A23B (Reflection AI) — 47.3](https://modelscale.dev/models/reflection-beam) - [Grok 4.3 (xAI) — 46.7](https://modelscale.dev/models/grok-4-3) - [Claude Sonnet 4.5 (Anthropic) — 46.6](https://modelscale.dev/models/claude-sonnet-4-5) - [Claude Sonnet 4.5 Thinking (Anthropic) — 46.6](https://modelscale.dev/models/claude-sonnet-4-5-thinking) - [Qwen3.5 397B (Alibaba) — 46.5](https://modelscale.dev/models/qwen3-5-397b) - [Laguna S 2.1 (Poolside) — 46.5](https://modelscale.dev/models/laguna-s-2-1) - [Nemotron 3 Nano 30B (NVIDIA) — 51.59](https://modelscale.dev/models/nemotron-3-nano-30b) - [Nemotron 3.5 Super VL 120B A12B (NVIDIA) — 46.3](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b) - [Ternary Bonsai 2 27B (Prism ML) — 46](https://modelscale.dev/models/ternary-bonsai-2-27b) - [GPT-5.1-Codex-Max (OpenAI) — 45.9](https://modelscale.dev/models/gpt-5-1-codex-max) - [GLM-5 (Z.AI) — 45.8](https://modelscale.dev/models/glm-5) - [Ling 3.0 Flash VL (InclusionAI) — 46.79](https://modelscale.dev/models/ling-3-0-flash-vl) - [Grok 4.1 Fast (Reasoning) (xAI) — 45.7](https://modelscale.dev/models/grok-4-1-fast-reasoning) - [GPT-5.1-Codex (OpenAI) — 45.5](https://modelscale.dev/models/gpt-5-1-codex) - [GLM-5-Turbo (Z.AI) — 45.5](https://modelscale.dev/models/glm-5-turbo) - [Grok 4 Fast (Reasoning) (xAI) — 45.2](https://modelscale.dev/models/grok-4-fast-reasoning) - [GPT-5.4 nano (OpenAI) — 44.5](https://modelscale.dev/models/gpt-5-4-nano) - [Muse Glimmer 30B (Meta) — 44.4](https://modelscale.dev/models/muse-glimmer-30b) - [GPT-5 (medium) (OpenAI) — 44.64](https://modelscale.dev/models/gpt-5-medium) - [Claude 4.1 Opus (Anthropic) — 44.1](https://modelscale.dev/models/claude-4-1-opus) - [Gemini 2.5 Flash (Google) — 44.1](https://modelscale.dev/models/gemini-2-5-flash) - [Qwen3.7 Flash (Alibaba) — 44](https://modelscale.dev/models/qwen3-7-flash) - [DeepSeek Coder 2.0 (DeepSeek) — 48.97](https://modelscale.dev/models/deepseek-coder-2-0) - [Qwen3.6-27B (Alibaba) — 43.9](https://modelscale.dev/models/qwen3-6-27b) - [Kimi K2.5 (Moonshot AI) — 43.9](https://modelscale.dev/models/kimi-k2-5) - [Seed 1.6 (ByteDance) — 48.92](https://modelscale.dev/models/seed-1-6) - [o1 (OpenAI) — 43.8](https://modelscale.dev/models/o1) - [Qwen3.5 Plus (Alibaba) — 43.7](https://modelscale.dev/models/qwen3-5-plus) - [Mistral Medium 3.5 128B (Mistral) — 43.7](https://modelscale.dev/models/mistral-medium-3-5-128b) - [o4-mini (high) (OpenAI) — 48.68](https://modelscale.dev/models/o4-mini-high) - [Nemotron 3.5 Bolt 74B-A9B (NVIDIA) — 43.6](https://modelscale.dev/models/nemotron-3-5-bolt-74b-a9b) - [DeepSeekMath V2 (DeepSeek) — 48.58](https://modelscale.dev/models/deepseekmath-v2) - [o3-mini (OpenAI) — 43.6](https://modelscale.dev/models/o3-mini) - [Qwen2.5-1M (Alibaba) — 48.58](https://modelscale.dev/models/qwen2-5-1m) - [DeepSeek-R1 (DeepSeek) — 43.4](https://modelscale.dev/models/deepseek-r1) - [Seed-2.0-Lite (ByteDance) — 48.53](https://modelscale.dev/models/seed-2-0-lite) - [Qwen3.5-122B-A10B (Alibaba) — 43.3](https://modelscale.dev/models/qwen3-5-122b-a10b) - [GLM-4.7 (Z.AI) — 43.3](https://modelscale.dev/models/glm-4-7) - [Gemini 2.5 Pro (Google) — 43.1](https://modelscale.dev/models/gemini-2-5-pro) - [Ministral 3 14B (Reasoning) (Mistral) — 48.05](https://modelscale.dev/models/ministral-3-14b-reasoning) - [Gemma 4 31B (Google) — 43](https://modelscale.dev/models/gemma-4-31b) - [MiniMax M2.7 (MiniMax) — 42](https://modelscale.dev/models/minimax-m2-7) - [MiMo-V2-Pro (Xiaomi) — 41.9](https://modelscale.dev/models/mimo-v2-pro) - [Solar Pro 3 (Upstage) — 41.8](https://modelscale.dev/models/solar-pro-3) - [GPT-5 mini (OpenAI) — 41.6](https://modelscale.dev/models/gpt-5-mini) - [Aion-2.0 (Aion Labs) — 47.37](https://modelscale.dev/models/aion-2-0) - [LFM2.5-24B-A2B (LiquidAI) — 41.5](https://modelscale.dev/models/lfm2-5-24b-a2b) - [o1-preview (OpenAI) — 43.5](https://modelscale.dev/models/o1-preview) - [Gemini 3.1 Flash-Lite (Google) — 41.4](https://modelscale.dev/models/gemini-3-1-flash-lite) - [Claude 4 Sonnet (Anthropic) — 41.1](https://modelscale.dev/models/claude-4-sonnet) - [DeepSeek V3.1 (Reasoning) (DeepSeek) — 39.21](https://modelscale.dev/models/deepseek-v3-1-reasoning) - [GPT-5 nano (OpenAI) — 40.9](https://modelscale.dev/models/gpt-5-nano) - [MiniMax M1 80k (MiniMax) — 40.8](https://modelscale.dev/models/minimax-m1-80k) - [Grok 3 Mini (xAI) — 40.8](https://modelscale.dev/models/grok-3-mini) - [Spark-X2.6-4B (SparkLLM) — 40.6](https://modelscale.dev/models/spark-x2-6-4b) - [Claude 4.1 Opus Thinking (Anthropic) — 37.77](https://modelscale.dev/models/claude-4-1-opus-thinking) - [Grok 4.1 Fast (xAI) — 40.5](https://modelscale.dev/models/grok-4-1-fast) - [Phi-4 (Microsoft) — 42.2](https://modelscale.dev/models/phi-4) - [Qwen3.5-27B (Alibaba) — 40](https://modelscale.dev/models/qwen3-5-27b) - [DeepSeek V3.2 (DeepSeek) — 40](https://modelscale.dev/models/deepseek-v3-2) - [Z-1 (Z) — 43.9](https://modelscale.dev/models/z-1) - [Qwen3.6-35B-A3B (Alibaba) — 39.9](https://modelscale.dev/models/qwen3-6-35b-a3b) - [o1-pro (OpenAI) — 36.32](https://modelscale.dev/models/o1-pro) - [Seed 1.6 Flash (ByteDance) — 43.86](https://modelscale.dev/models/seed-1-6-flash) - [Grok Code Fast 1 (xAI) — 39.8](https://modelscale.dev/models/grok-code-fast-1) - [Mistral 8x7B (Mistral) — 43.76](https://modelscale.dev/models/mistral-8x7b) - [DeepSeek V3.1 (DeepSeek) — 39.7](https://modelscale.dev/models/deepseek-v3-1) - [Mercury 2.5 (Inception) — 39.6](https://modelscale.dev/models/mercury-2-5) - [Mixtral 8x22B Instruct v0.1 (Mistral) — 41.1](https://modelscale.dev/models/mixtral-8x22b-instruct-v0-1) - [Moonshot v1 (Moonshot AI) — 43.57](https://modelscale.dev/models/moonshot-v1) - [MiMo-V2-Flash (Xiaomi) — 39.1](https://modelscale.dev/models/mimo-v2-flash) - [Seed-2.0-Mini (ByteDance) — 43.38](https://modelscale.dev/models/seed-2-0-mini) - [LFM2.5-2.6B (LiquidAI) — 39](https://modelscale.dev/models/lfm2-5-2-6b) - [MiniMax M2.5 (MiniMax) — 39](https://modelscale.dev/models/minimax-m2-5) - [Nemotron Ultra 253B (NVIDIA) — 43.18](https://modelscale.dev/models/nemotron-ultra-253b) - [GLM-4.5 (Z.AI) — 39](https://modelscale.dev/models/glm-4-5) - [GLM-5V-Turbo (Z.AI) — 38.8](https://modelscale.dev/models/glm-5v-turbo) - [GLM-4.6 (Z.AI) — 40.7](https://modelscale.dev/models/glm-4-6) - [Claude 3.5 Sonnet (Anthropic) — 38.6](https://modelscale.dev/models/claude-3-5-sonnet) - [Hy3 Preview (Tencent) — 38.5](https://modelscale.dev/models/hy3-preview) - [Grok 3 Beta (xAI) — 38.5](https://modelscale.dev/models/grok-3-beta) - [Gemma 4 26B A4B (Google) — 38.1](https://modelscale.dev/models/gemma-4-26b-a4b) - [Mistral Large 3 (Mistral) — 37.6](https://modelscale.dev/models/mistral-large-3) - [GLM-4.5-Air (Z.AI) — 39.6](https://modelscale.dev/models/glm-4-5-air) - [DeepSeek R1 Distill Qwen 32B (DeepSeek) — 30.43](https://modelscale.dev/models/deepseek-r1-distill-qwen-32b) - [GLM-4.7-Flash (Z.AI) — 37.5](https://modelscale.dev/models/glm-4-7-flash) - [Qwen3.5 Flash (Alibaba) — 37.4](https://modelscale.dev/models/qwen3-5-flash) - [Mistral Large 2 (Mistral) — 37.3](https://modelscale.dev/models/mistral-large-2) - [DeepSeek V3 (DeepSeek) — 37.2](https://modelscale.dev/models/deepseek-v3) - [Qwen3 Max (Alibaba) — 36.7](https://modelscale.dev/models/qwen3-max) - [LFM2.5-8B-A1B (LiquidAI) — 36.4](https://modelscale.dev/models/lfm2-5-8b-a1b) - [Qwen2.5-72B (Alibaba) — 28.07](https://modelscale.dev/models/qwen2-5-72b) - [Mercury 2 (Inception) — 36.3](https://modelscale.dev/models/mercury-2) - [Ornith-1.5-9B (Ornith AI) — 36.1](https://modelscale.dev/models/ornith-1-5-9b) - [GPT-4.1 (OpenAI) — 35.8](https://modelscale.dev/models/gpt-4-1) - [DeepSeek V3 0324 (DeepSeek) — 37.5](https://modelscale.dev/models/deepseek-v3-0324) - [GPT-OSS 120B (OpenAI) — 35.4](https://modelscale.dev/models/gpt-oss-120b) - [Llama 3.1 405B (Meta) — 27.53](https://modelscale.dev/models/llama-3-1-405b) - [Ministral 3 8B (Reasoning) (Mistral) — 39.23](https://modelscale.dev/models/ministral-3-8b-reasoning) - [Gemini 1.5 Pro (Google) — 35.3](https://modelscale.dev/models/gemini-1-5-pro) - [Qwen3 235B 2507 (Alibaba) — 34.9](https://modelscale.dev/models/qwen3-235b-2507) - [Celeris-1 (Celeris) — 27](https://modelscale.dev/models/celeris-1) - [Qwen2.5-VL-32B (Alibaba) — 38.7](https://modelscale.dev/models/qwen2-5-vl-32b) - [Claude 3 Haiku (Anthropic) — 34.7](https://modelscale.dev/models/claude-3-haiku) - [Llama 4 Behemoth (Meta) — 38.66](https://modelscale.dev/models/llama-4-behemoth) - [Qwen3.5-35B-A3B (Alibaba) — 34.7](https://modelscale.dev/models/qwen3-5-35b-a3b) - [Granite-4.0-1B (IBM) — 38.06](https://modelscale.dev/models/granite-4-0-1b) - [Mistral Medium 3 (Mistral) — 34.6](https://modelscale.dev/models/mistral-medium-3) - [Command A+ (Cohere) — 28.25](https://modelscale.dev/models/command-a-plus) - [Kimi K2 (Moonshot AI) — 34.2](https://modelscale.dev/models/kimi-k2) - [Gemma 4 E2B (Google) — 33.9](https://modelscale.dev/models/gemma-4-e2b) - [Granite-4.0-H-1B (IBM) — 28.78](https://modelscale.dev/models/granite-4-0-h-1b) - [Ministral 3 3B (Reasoning) (Mistral) — 38.37](https://modelscale.dev/models/ministral-3-3b-reasoning) - [Gemma 4 E4B (Google) — 33.9](https://modelscale.dev/models/gemma-4-e4b) - [GPT-4 Turbo (OpenAI) — 33.8](https://modelscale.dev/models/gpt-4-turbo) - [Qwen2.5 Coder 32B Instruct (Alibaba) — 25.94](https://modelscale.dev/models/qwen2-5-coder-32b-instruct) - [Claude Haiku 4.5 (Anthropic) — 33.8](https://modelscale.dev/models/claude-haiku-4-5) - [Laguna XS.2 (Poolside) — 0.48](https://modelscale.dev/models/laguna-xs-2) - [Mistral 8x7B v0.2 (Mistral) — 37.99](https://modelscale.dev/models/mistral-8x7b-v0-2) - [Claude Haiku 4.5 Thinking (Anthropic) — 33.8](https://modelscale.dev/models/claude-haiku-4-5-thinking) - [Mistral Small 4 (Mistral) — 25.74](https://modelscale.dev/models/mistral-small-4) - [Laguna M.1 (Poolside) — 0.31](https://modelscale.dev/models/laguna-m-1) - [Gemma 3 27B (Google) — 33.5](https://modelscale.dev/models/gemma-3-27b) - [Granite-4.0-350M (IBM) — 28.42](https://modelscale.dev/models/granite-4-0-350m) - [Llama 4 Scout (Meta) — 33.3](https://modelscale.dev/models/llama-4-scout) - [Granite-4.0-H-350M (IBM) — 28.42](https://modelscale.dev/models/granite-4-0-h-350m) - [GPT-4.1 mini (OpenAI) — 33](https://modelscale.dev/models/gpt-4-1-mini) - [Nemotron 3 Nano Omni 30B A3B (NVIDIA) — 32.9](https://modelscale.dev/models/nemotron-3-nano-omni-30b-a3b) - [Nemotron 3 Super 100B (NVIDIA) — 32.3](https://modelscale.dev/models/nemotron-3-super-100b) - [Granite 4.2 8B (IBM) — 31.1](https://modelscale.dev/models/granite-4-2-8b) - [LFM3-1.7B (LiquidAI) — 30.9](https://modelscale.dev/models/lfm3-1-7b) - [Claude 3 Opus (Anthropic) — 30.5](https://modelscale.dev/models/claude-3-opus) - [Qwen3-Omni-30B-A3B-Instruct (Alibaba) — 28.07](https://modelscale.dev/models/qwen3-omni-30b-a3b-instruct) - [Trinity-Large-Thinking (Arcee AI) — 30.5](https://modelscale.dev/models/trinity-large-thinking) - [GPT-4o (OpenAI) — 30.3](https://modelscale.dev/models/gpt-4o) - [Nova Pro (Amazon) — 20.99](https://modelscale.dev/models/nova-pro) - [GPT-OSS 20B (OpenAI) — 30](https://modelscale.dev/models/gpt-oss-20b) - [GPT-4o mini (OpenAI) — 29.9](https://modelscale.dev/models/gpt-4o-mini) - [Llama 3 70B (Meta) — 20.36](https://modelscale.dev/models/llama-3-70b) - [Llama 4 Maverick (Meta) — 28.8](https://modelscale.dev/models/llama-4-maverick) - [Nemotron 3.5 Lightning 30B A3B NVFP4 (NVIDIA) — 27.5](https://modelscale.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) - [MiMo-V2-Omni (Xiaomi) — 29.2](https://modelscale.dev/models/mimo-v2-omni) - [Gemma 4 12B (Google) — 26.9](https://modelscale.dev/models/gemma-4-12b) - [Ministral 3 14B (Mistral) — 24.85](https://modelscale.dev/models/ministral-3-14b) - [Sarvam 105B (Sarvam) — 26](https://modelscale.dev/models/sarvam-105b) - [Gemini 1.0 Pro (Google) — 11.17](https://modelscale.dev/models/gemini-1-0-pro) - [Nemotron 3 Super 120B A12B (NVIDIA) — 25.9](https://modelscale.dev/models/nemotron-3-super-120b-a12b) - [Nemotron-4 15B (NVIDIA) — 9.76](https://modelscale.dev/models/nemotron-4-15b) - [Sarvam 30B (Sarvam) — 25](https://modelscale.dev/models/sarvam-30b) - [Mistral 7B v0.3 (Mistral) — 7.05](https://modelscale.dev/models/mistral-7b-v0-3) - [ZAYA1-8B (Zyphra) — 24.5](https://modelscale.dev/models/zaya1-8b) - [GPT-4.1 nano (OpenAI) — 21.2](https://modelscale.dev/models/gpt-4-1-nano) - [LFM2-24B-A2B (LiquidAI) — 20.57](https://modelscale.dev/models/lfm2-24b-a2b) - [MiniCPM5-1B (OpenBMB) — 13.4](https://modelscale.dev/models/minicpm5-1b) - [Ministral 3 8B (Mistral) — 19.95](https://modelscale.dev/models/ministral-3-8b) - [LFM2.5-1.2B-Thinking (LiquidAI) — 19.33](https://modelscale.dev/models/lfm2-5-1-2b-thinking) - [LFM2.5-1.2B-Instruct (LiquidAI) — 19.08](https://modelscale.dev/models/lfm2-5-1-2b-instruct) - [Ministral 3 3B (Mistral) — 18.78](https://modelscale.dev/models/ministral-3-3b) - [1-bit Bonsai 1.7B (Prism ML)](https://modelscale.dev/models/bonsai-1-7b) - [1-bit Bonsai 27B (Prism ML)](https://modelscale.dev/models/bonsai-27b) - [1-bit Bonsai 4B (Prism ML)](https://modelscale.dev/models/bonsai-4b) - [1-bit Bonsai 8B (Prism ML)](https://modelscale.dev/models/bonsai-8b) - [A.X K2 (SK Telecom)](https://modelscale.dev/models/a-x-k2) - [A.X series (SK Telecom)](https://modelscale.dev/models/skt-ax) - [Agents-A1-4B (InternScience)](https://modelscale.dev/models/agents-a1-4b) - [AJev lora5 (Gemma 4 12B) (andyzhang232)](https://modelscale.dev/models/decision-index-0-3-ajev-lora5-gemma-4-12b) - [Alibaba GTE Reranker ModernBERT-base (Alibaba)](https://modelscale.dev/models/gte-reranker-modernbert-base) - [Alibaba GTE Reranker ModernBERT-base (Alibaba-NLP)](https://modelscale.dev/models/jevbench-gte-reranker-modernbert-base) - [Amazon Nova 2 Lite (Amazon)](https://modelscale.dev/models/nova-2-lite) - [Amazon Nova 2 Pro (Amazon)](https://modelscale.dev/models/nova-2-pro) - [Amazon Nova 2 Sonic (Amazon)](https://modelscale.dev/models/amazon-nova-2-sonic) - [Apodex 1.1 Mini (Apodex)](https://modelscale.dev/models/apodex-1-1-mini) - [Arena-Hard (claude-3-5-sonnet-20240620) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-claude-3-5-sonnet-20240620) - [Arena-Hard (claude-3-haiku-20240307) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-claude-3-haiku-20240307) - [Arena-Hard (DeepSeek-R1-250120) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-deepseek-r1-250120) - [Arena-Hard (gemini-1.5-flash-001) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-gemini-1-5-flash-001) - [Arena-Hard (gemini-1.5-pro-001) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-gemini-1-5-pro-001) - [Arena-Hard (gpt-4o-2024-05-13) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-gpt-4o-2024-05-13) - [Arena-Hard (gpt-4o-mini-2024-07-18) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-gpt-4o-mini-2024-07-18) - [Arena-Hard (Llama-3.1-405B-Instruct) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-llama-3-1-405b-instruct) - [Arena-Hard (Llama-3.1-70B-Instruct) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-llama-3-1-70b-instruct) - [Arena-Hard (Llama-3.1-8B-Instruct) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-llama-3-1-8b-instruct) - [Arena-Hard (Mistral-7B-v0.1-Instruct) (JudgeBench) (JudgeBench evaluated system)](https://modelscale.dev/models/native-judgebench-arena-hard-mistral-7b-v0-1-instruct) - [Arena-Hard (o1-mini-2024-09-12) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-o1-mini-2024-09-12) - [Arena-Hard (o1-preview-2024-09-12) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-o1-preview-2024-09-12) - [Arena-Hard (o3-mini-2025-01-31 (high)) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-o3-mini-2025-01-31-high) - [Arena-Hard (o3-mini-2025-01-31 (low)) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-o3-mini-2025-01-31-low) - [Arena-Hard (o3-mini-2025-01-31 (medium)) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-arena-hard-o3-mini-2025-01-31-medium) - [Atria Dawn Preview (Shanghai Artificial Intelligence Laboratory)](https://modelscale.dev/models/atria-dawn-preview) - [Audio Flamingo 3 7B (NVIDIA)](https://modelscale.dev/models/audio-flamingo-3-7b) - [AuK (Tencent)](https://modelscale.dev/models/tencent-auk) - [Auto-J (JudgeBench) (GAIR)](https://modelscale.dev/models/native-judgebench-auto-j) - [AutoJev-27B (denis-pplx)](https://modelscale.dev/models/autojev-27b) - [AutoJev-27B (Decision Index reference) (denis-pplx)](https://modelscale.dev/models/decision-index-autojev-27b) - [AutoJev-27B (denis-pplx, Qwen3.8-27B) (unknown)](https://modelscale.dev/models/jevbench-autojev-27b) - [AutoJev-27B (RTX PRO 6000) (denis-pplx)](https://modelscale.dev/models/autojev-27b-rtxpro6000-a2) - [AutoJev-27B (RTX PRO 6000) (unknown)](https://modelscale.dev/models/jevbench-autojev-27b-rtxpro6000-a2) - [Autoloops – Gemma 4 31B IT (Autoloops)](https://modelscale.dev/models/jevbench-kushal-gemma4-31b-it-autoloops) - [Autoloops Gemma 4 31B IT (Autoloops)](https://modelscale.dev/models/autoloops-gemma-4-31b-it) - [BAAI bge-reranker-v2-m3 (BAAI)](https://modelscale.dev/models/bge-reranker-v2-m3) - [BAAI bge-reranker-v2-m3 (BAAI)](https://modelscale.dev/models/jevbench-bge-reranker-v2-m3) - [Baichuan-Audio (Baichuan)](https://modelscale.dev/models/baichuan-audio) - [Baichuan-Omni 1.5 (Baichuan)](https://modelscale.dev/models/baichuan-omni-1-5) - [Beam 1.0 501B-A23B FP8 (Reflection AI)](https://modelscale.dev/models/reflection-beam-fp8) - [Beam 1.0 501B-A23B NVFP4 (Reflection AI)](https://modelscale.dev/models/reflection-beam-nvfp4) - [Bekko System One v0 17M (hotchpotch)](https://modelscale.dev/models/decision-index-0-3-bekko-system-one-v0-17m) - [Bekko System One v0 400M (hotchpotch)](https://modelscale.dev/models/decision-index-0-3-bekko-system-one-v0-400m) - [Bekko System One v0 68M (hotchpotch)](https://modelscale.dev/models/decision-index-0-3-bekko-system-one-v0-68m) - [BERT base / Fine-tuned on case law and contract corpora Chalkidis et al. (2020) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-bert-base-fine-tuned-on-case-law-and-contract-corpora-chalkidis-et-al-2020) - [BERT base / Fine-tuned on NDAs (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-bert-base-fine-tuned-on-ndas) - [BERT base / None (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-bert-base-none) - [BERT base / Pretrained from scratch using a case law corpus Zheng et al. (2021) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-bert-base-pretrained-from-scratch-using-a-case-law-corpus-zheng-et-al-2021) - [BERT classifier w/o Table (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-bert-classifier-w-o-table) - [BERT large / Fine-tuned on NDAs (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-bert-large-fine-tuned-on-ndas) - [BERT large / None (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-bert-large-none) - [BERT-BOOLQ-YN (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-bert-boolq-yn) - [BERT-DIS-YN (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-bert-dis-yn) - [BERT-MNLI-YN (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-bert-mnli-yn) - [BERT-YN (Answer) (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-bert-yn-answer) - [BERT-YN (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-bert-yn) - [BERT-YN (Question) (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-bert-yn-question) - [Bespoke Nimble 9B (Bespoke Labs)](https://modelscale.dev/models/nimble-9b) - [Bespoke Nimble 9B (Bespoke Labs) (Bespoke Labs)](https://modelscale.dev/models/jevbench-nimble-9b) - [Bespoke Nimble 9B v2 (bespokelabs)](https://modelscale.dev/models/decision-index-0-3-bespoke-nimble-9b-v2) - [Bespoke Nimble 9B v3 (bespokelabs)](https://modelscale.dev/models/decision-index-0-3-bespoke-nimble-9b-v3) - [Bev / Bonsai 27B (Reza Sayar)](https://modelscale.dev/models/bev-bonsai-27b) - [Bev / Bonsai 27B (Reza Sayar)](https://modelscale.dev/models/jevbench-bev-bonsai-27b) - [Bland Speech v3 (Bland AI)](https://modelscale.dev/models/bland-speech-v3) - [Blink v0.3 26B-A4B (NVFP4) (PixilabAI)](https://modelscale.dev/models/decision-index-0-3-blink-v0-3-26b-a4b-nvfp4) - [BLOOMZ 7.1B (Belebele zero-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-bloomz-7-1b-zero-shot) - [BLSP 7B (BLSP authors)](https://modelscale.dev/models/blsp-7b) - [BOOLQ (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-boolq) - [Bosun v3.1 0.6B (Clause Logic)](https://modelscale.dev/models/bosun-v31-0-6b) - [Bosun v3.1 0.6B (Clause Logic)](https://modelscale.dev/models/jevbench-bosun-v31-0-6b) - [Bosun v3.1 1.7B (Hanno-Labs)](https://modelscale.dev/models/decision-index-0-3-bosun-v3-1-1-7b) - [BR-Voice-Reasoner (Bairong Xdynamics)](https://modelscale.dev/models/br-voice-reasoner) - [BTL-3 (Bad Theory Labs)](https://modelscale.dev/models/btl-3) - [BTL-4 (Bad Theory Labs)](https://modelscale.dev/models/btl-4) - [BTL-4 Compact (Bad Theory Labs)](https://modelscale.dev/models/btl-4-compact) - [Canary 180M Flash (NVIDIA)](https://modelscale.dev/models/canary-180m-flash) - [Cartesia Ink-Whisper (Cartesia)](https://modelscale.dev/models/cartesia-ink-whisper) - [Cartesia Sonic 3 (Cartesia)](https://modelscale.dev/models/cartesia-sonic-3) - [Cartesia Sonic 3.5 (Cartesia)](https://modelscale.dev/models/cartesia-sonic-3-5) - [Cartesia Sonic 3.6 (Cartesia)](https://modelscale.dev/models/cartesia-sonic-3-6) - [Celeris-1 Decision (Celeris)](https://modelscale.dev/models/celeris-1-decision) - [Celeris-1.1 Decision (Celeris)](https://modelscale.dev/models/celeris-1-1-decision) - [Certo v1 (AltSlate Labs)](https://modelscale.dev/models/certo) - [Certo v1 (AltSlate Labs) (AltSlate Labs)](https://modelscale.dev/models/jevbench-certo) - [ChatEval (gpt-4o-2024-05-13) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-chateval-gpt-4o-2024-05-13) - [classifier.dev (fast tier) (mrmps (@michael_chomsky))](https://modelscale.dev/models/jevbench-classifier-dev-fast) - [classifier.dev (fast) (classifier.dev)](https://modelscale.dev/models/classifier-dev-fast) - [Claude 3.5 Haiku (Anthropic)](https://modelscale.dev/models/claude-3-5-haiku) - [Claude 3.7 Sonnet (Anthropic)](https://modelscale.dev/models/claude-3-7-sonnet) - [Claude 3.7 Sonnet Thinking (Anthropic)](https://modelscale.dev/models/claude-3-7-sonnet-thinking) - [Claude 4 Opus (Anthropic)](https://modelscale.dev/models/claude-4-opus) - [Claude 4 Opus Thinking (Anthropic)](https://modelscale.dev/models/claude-4-opus-thinking) - [Claude Mythos 5 (Anthropic)](https://modelscale.dev/models/claude-mythos-5) - [Claude Mythos 5.1 (Anthropic)](https://modelscale.dev/models/claude-mythos-5-1) - [Claude Mythos 5.2 (Anthropic)](https://modelscale.dev/models/claude-mythos-5-2) - [Claude Mythos Preview (Anthropic)](https://modelscale.dev/models/claude-mythos-preview) - [Claude-3.5-Sonnet Solver (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-claude-3-5-sonnet-solver) - [Clef (Cloudflare)](https://modelscale.dev/models/cloudflare-clef) - [Clef-Flash (Cloudflare)](https://modelscale.dev/models/cloudflare-clef-flash) - [Clef-Omni (Cloudflare)](https://modelscale.dev/models/cloudflare-clef-omni) - [CLM-8B (Contrastive-LM)](https://modelscale.dev/models/clm-8b) - [CLM-8B (Contrastive-LM, clm-latest) (Contrastive-LM (Kwok, Kang, Suresh, Saad-Falcon, Pavone, Ré, Mirhoseini))](https://modelscale.dev/models/jevbench-clm-8b) - [CLM-v0.1-8B (Contrastive-LM)](https://modelscale.dev/models/decision-index-0-3-clm-v0-1-8b) - [Cohere Transcribe 03-2026 (Cohere)](https://modelscale.dev/models/cohere-transcribe-03-2026) - [Cohere Transcribe Arabic 07-2026 (Cohere)](https://modelscale.dev/models/cohere-transcribe-arabic-07-2026) - [CompassJudger-1-1.5B (JudgeBench) (OpenCompass)](https://modelscale.dev/models/native-judgebench-compassjudger-1-1-5b) - [CompassJudger-1-14B (JudgeBench) (OpenCompass)](https://modelscale.dev/models/native-judgebench-compassjudger-1-14b) - [CompassJudger-1-32B (JudgeBench) (OpenCompass)](https://modelscale.dev/models/native-judgebench-compassjudger-1-32b) - [CompassJudger-1-7B (JudgeBench) (OpenCompass)](https://modelscale.dev/models/native-judgebench-compassjudger-1-7b) - [Composer 2 (Cursor)](https://modelscale.dev/models/composer-2) - [Composer 2 Fast (Cursor)](https://modelscale.dev/models/composer-2-fast) - [Composer 2.5 (Cursor)](https://modelscale.dev/models/composer-2-5) - [Cosmos3-Edge (NVIDIA)](https://modelscale.dev/models/cosmos3-edge) - [Cosmos3-Nano (NVIDIA)](https://modelscale.dev/models/cosmos3-nano) - [Cosmos3-Super (NVIDIA)](https://modelscale.dev/models/cosmos3-super) - [Cygnet (blockbrain)](https://modelscale.dev/models/cygnet) - [Cygnet (blockbrain, frozen Gemma-4-12B-it) (blockbrain)](https://modelscale.dev/models/jevbench-cygnet) - [d1 (Liquid AI)](https://modelscale.dev/models/liquid-d1) - [d1-2B (LiquidAI)](https://modelscale.dev/models/d1-2b) - [d1-3B (LiquidAI)](https://modelscale.dev/models/d1-3b) - [d1-Omni-2B (LiquidAI)](https://modelscale.dev/models/d1-omni-2b) - [d1-omni-600M (LiquidAI)](https://modelscale.dev/models/d1-omni-600m) - [d1-ultra (Liquid AI)](https://modelscale.dev/models/d1-ultra) - [d1.2 (Liquid AI)](https://modelscale.dev/models/liquid-d1-2) - [d1.2-ultra (Liquid AI)](https://modelscale.dev/models/liquid-d1-2-ultra) - [DBRX Instruct (Databricks)](https://modelscale.dev/models/dbrx-instruct) - [DeBERTa v2 xlarge / Fine-tuned on span identification Hendrycks et al. (2021) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-deberta-v2-xlarge-fine-tuned-on-span-identification-hendrycks-et-al-2021) - [DeBERTa v2 xlarge / None (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-deberta-v2-xlarge-none) - [Decider 4B (Mapika)](https://modelscale.dev/models/decision-index-0-3-decider-4b) - [Decider chat · Gemma-4-31B (Mapika)](https://modelscale.dev/models/decision-index-decider-chat-gemma4-31b) - [Decider chat · Qwen3.6-27B (Not listed)](https://modelscale.dev/models/decision-index-0-3-decider-chat-qwen3-6-27b) - [decider-2b (Mapika)](https://modelscale.dev/models/decider-2b) - [decider-2b (Mapika) (Mapika)](https://modelscale.dev/models/jevbench-decider-2b) - [decider-35b-a3b (Mapika)](https://modelscale.dev/models/decider-35b-a3b) - [decider-35b-a3b (Mapika) (Mapika)](https://modelscale.dev/models/jevbench-decider-35b-a3b) - [decider-4b v2 (Mapika)](https://modelscale.dev/models/decider-4b-v2) - [decider-4b v2 (Mapika) (Mapika)](https://modelscale.dev/models/jevbench-decider-4b-v2) - [decisio 0.4.0 (Gemma 4 12B) (Not listed)](https://modelscale.dev/models/decision-index-0-3-decisio-0-4-0-gemma-4-12b) - [decisio 0.4.0 (Qwen3.6-35B-A3B) (Not listed)](https://modelscale.dev/models/decision-index-0-3-decisio-0-4-0-qwen3-6-35b-a3b) - [Decision 2B (FlyMy.AI, v59) (FlyMy.AI (@denti))](https://modelscale.dev/models/jevbench-decision-2b) - [Decision 2B v59 (FlyMy.AI)](https://modelscale.dev/models/decision-2b) - [Decision 4B v1.1 (FlyMy.AI)](https://modelscale.dev/models/decision-4b-v11) - [Decision 4B v1.1 (FlyMyJev, Qwen3.5-4B + LoRA) (unknown)](https://modelscale.dev/models/jevbench-decision-4b-v11) - [Decision 4B v1.2 (FlyMy.AI)](https://modelscale.dev/models/decision-4b-v12) - [Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) (unknown)](https://modelscale.dev/models/jevbench-decision-4b-v12) - [Decision Fast (FlyMy.AI, v53a) (FlyMy.AI (@denti))](https://modelscale.dev/models/jevbench-decision-fast) - [Decision Fast v53a (FlyMy.AI)](https://modelscale.dev/models/decision-fast) - [Decision-4B (Eval Engine / Chromia) (Eval Engine / Chromia)](https://modelscale.dev/models/evalengine-decision-4b) - [Decision-4B (Eval Engine / Chromia) (Eval Engine / Chromia)](https://modelscale.dev/models/jevbench-evalengine-decision-4b) - [decision-machine-1 (milliseconds.ai)](https://modelscale.dev/models/decision-machine-1) - [decision-machine-1 (milliseconds.ai) (milliseconds.ai (Baptiste Laget))](https://modelscale.dev/models/jevbench-decision-machine-1) - [deck31b (Gemma 4 31B) (Not listed)](https://modelscale.dev/models/decision-index-0-3-deck31b-gemma-4-31b) - [Deem 0.8B v1 (LibertAI)](https://modelscale.dev/models/deem-0-8-v1) - [Deem 0.8B v1 (LibertAI)](https://modelscale.dev/models/jevbench-deem-0-8-v1) - [Deepgram Aura-2 (Deepgram)](https://modelscale.dev/models/deepgram-aura-2) - [Deepgram Flux (Deepgram)](https://modelscale.dev/models/deepgram-flux) - [Deepgram Flux Multilingual (Deepgram)](https://modelscale.dev/models/deepgram-flux-multilingual) - [Deepgram Nova-3 (Deepgram)](https://modelscale.dev/models/deepgram-nova-3) - [DeepSeek R1 Distill Llama 70B (DeepSeek)](https://modelscale.dev/models/deepseek-r1-distill-llama-70b) - [DeepSeek R1 Distill Qwen 14B (DeepSeek)](https://modelscale.dev/models/deepseek-r1-distill-qwen-14b) - [DeepSeek V4 Flash 0731 (DeepSeek)](https://modelscale.dev/models/deepseek-v4-flash-max) - [DeepSeek-R1-0528 (DeepSeek)](https://modelscale.dev/models/deepseek-r1-0528) - [DeepSeek-R1-0528-Qwen3-8B (DeepSeek)](https://modelscale.dev/models/deepseek-r1-0528-qwen3-8b) - [DeepSeek-V2.5 (DeepSeek)](https://modelscale.dev/models/deepseek-v2-5) - [Dessa (Block)](https://modelscale.dev/models/dessa) - [Devstral Small (Mistral)](https://modelscale.dev/models/devstral-small) - [Dinah-0 (Lukitaduarte)](https://modelscale.dev/models/decision-index-0-3-dinah-0) - [DiVA Llama 3 8B (DiVA authors)](https://modelscale.dev/models/diva-llama-3-v0-8b) - [djev (Maisa)](https://modelscale.dev/models/djev) - [djev (Maisa, diffusion-gemma) (Maisa (David Villalón))](https://modelscale.dev/models/jevbench-djev) - [djev (thinking) (Maisa)](https://modelscale.dev/models/djev-thinking) - [djev (thinking) (David Villalon / Maisa)](https://modelscale.dev/models/jevbench-djev-thinking) - [DM-JEPA 1.1 (Not listed)](https://modelscale.dev/models/decision-index-0-3-dm-jepa-1-1) - [DNA 1.0 8B (Community)](https://modelscale.dev/models/dna-1-0) - [Doc TF-IDF+SVM (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-doc-tf-idf-svm) - [Drex Max (Nace.AI)](https://modelscale.dev/models/drex-max) - [Drex Max v1.1 (Nace.AI)](https://modelscale.dev/models/drex-max-v1-1) - [Drex v1.5 (Nace.AI)](https://modelscale.dev/models/drex-v1-5) - [Drex v2.0 (Nace.AI)](https://modelscale.dev/models/drex-v2-0) - [Eikos-27B (caiovicentino1)](https://modelscale.dev/models/eikos-27b) - [Eikos-27B (caiovicentino1, Qwen3.8-27B) (unknown)](https://modelscale.dev/models/jevbench-eikos-27b) - [elephant-1 (Baseten)](https://modelscale.dev/models/elephant-1) - [Eleven Realtime v1 Max (ElevenLabs)](https://modelscale.dev/models/eleven-realtime-v1-max) - [Eleven Realtime v1 Mini (ElevenLabs)](https://modelscale.dev/models/eleven-realtime-v1-mini) - [ElevenLabs Eleven v3 (ElevenLabs)](https://modelscale.dev/models/elevenlabs-eleven-v3) - [ElevenLabs Eleven v3 Conversational (ElevenLabs)](https://modelscale.dev/models/elevenlabs-eleven-v3-conversational) - [ElevenLabs Eleven v4 (ElevenLabs)](https://modelscale.dev/models/elevenlabs-eleven-v4) - [ElevenLabs Eleven v4 Turbo (ElevenLabs)](https://modelscale.dev/models/elevenlabs-eleven-v4-turbo) - [Embed 5 Fast (Cohere)](https://modelscale.dev/models/cohere-embed-5-fast) - [Embed 5 Pro (Cohere)](https://modelscale.dev/models/cohere-embed-5-pro) - [EmbeddingGemma 2 (Google)](https://modelscale.dev/models/embeddinggemma-2) - [Ember-1 (Fireworks)](https://modelscale.dev/models/ember-1) - [ERNIE 5.5 Flash Preview (Baidu)](https://modelscale.dev/models/ernie-5-5-flash-preview) - [Exaone 4.0 1.2B (LG AI Research)](https://modelscale.dev/models/exaone-4-0-1-2b) - [Exaone 4.0 32B (LG AI Research)](https://modelscale.dev/models/exaone-4-0-32b) - [EXAONE-4.0-1.2B-JEV v0.3 (Not listed)](https://modelscale.dev/models/decision-index-0-3-exaone-4-0-1-2b-jev-v0-3) - [ezjev 4B s2 (everettjf)](https://modelscale.dev/models/decision-index-0-3-ezjev-4b-s2) - [Falcon 40B (Belebele 5-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-falcon-40b-5-shot) - [Fara1.5-27B (Microsoft)](https://modelscale.dev/models/fara-1-5-27b) - [Fara1.5-4B (Microsoft)](https://modelscale.dev/models/fara-1-5-4b) - [Fastino GLiDE no-thinking (28B) (Not listed)](https://modelscale.dev/models/decision-index-0-3-fastino-glide-no-thinking-28b) - [Finetuned Llama-2-13B (RAGTruth detector) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-finetuned-llama-2-13b-detector) - [Fish Audio S2.1 Pro (Fish Audio)](https://modelscale.dev/models/fish-audio-s2-1-pro) - [Flint (Recursive)](https://modelscale.dev/models/flint-40b-a2-5b) - [Freya TTS Adam V1 (Freya)](https://modelscale.dev/models/freya-tts-adam-v1) - [Fugu Cyber (Sakana AI)](https://modelscale.dev/models/sakana-fugu-cyber) - [Gemini 1.5 Flash (Google)](https://modelscale.dev/models/gemini-1-5-flash) - [Gemini 2.0 Flash (Google)](https://modelscale.dev/models/gemini-2-0-flash) - [Gemini 2.0 Flash-Lite (Google)](https://modelscale.dev/models/gemini-2-0-flash-lite) - [Gemini 2.5 Flash Native Audio Preview (12-2025) (Google)](https://modelscale.dev/models/gemini-2-5-flash-native-audio-preview-12-2025) - [Gemini 2.5 Flash TTS Preview (Google)](https://modelscale.dev/models/gemini-2-5-flash-tts-preview) - [Gemini 2.5 Flash-Lite (Google)](https://modelscale.dev/models/gemini-2-5-flash-lite) - [Gemini 2.5 Pro TTS Preview (Google)](https://modelscale.dev/models/gemini-2-5-pro-tts-preview) - [Gemini 3.1 Flash Live Preview (Google)](https://modelscale.dev/models/gemini-3-1-flash-live-preview) - [Gemini 3.1 Flash TTS Preview (Google)](https://modelscale.dev/models/gemini-3-1-flash-tts-preview) - [Gemini 3.5 Flash Cyber (Google)](https://modelscale.dev/models/gemini-3-5-flash-cyber) - [Gemini 3.5 Transcribe (Google)](https://modelscale.dev/models/gemini-3-5-transcribe) - [Gemini 3.8 Flash Cyber (Google)](https://modelscale.dev/models/gemini-3-8-flash-cyber) - [Gemini 3.8 Flash TTS (Google)](https://modelscale.dev/models/gemini-3-8-flash-tts) - [Gemini 3.8 Flash-Lite TTS (Google)](https://modelscale.dev/models/gemini-3-8-flash-lite-tts) - [Gemini 3.8 Live (Google)](https://modelscale.dev/models/gemini-3-8-live) - [Gemini 3.8 Live Extended Thinking (Google)](https://modelscale.dev/models/gemini-3-8-live-extended-thinking) - [Gemini Decision 1 (Google)](https://modelscale.dev/models/gemini-decision-1) - [Gemini Omni 1.1 Flash (Google)](https://modelscale.dev/models/gemini-omni-1-1-flash) - [Gemini Omni 1.2 Flash (Google)](https://modelscale.dev/models/gemini-omni-1-2-flash) - [Gemini-1.5-pro Solver (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-gemini-1-5-pro-solver) - [Gemma 2 27B (Google)](https://modelscale.dev/models/gemma-2-27b) - [GEV-26B-Decide (autotrust)](https://modelscale.dev/models/decision-index-0-3-gev-26b-decide) - [Gevva E2B (davidburhans)](https://modelscale.dev/models/decision-index-0-3-gevva-e2b) - [Gevva E4B (davidburhans)](https://modelscale.dev/models/decision-index-0-3-gevva-e4b) - [GLiDE (Fastino)](https://modelscale.dev/models/fastino-glide) - [GLiDE v1.2 (Fastino)](https://modelscale.dev/models/fastino-glide-v1-2) - [Glimpse (Elorian)](https://modelscale.dev/models/glimpse) - [GLiNER2 (Fastino, gliner2.5-base) (Fastino)](https://modelscale.dev/models/jevbench-gliner2) - [GLiNER2 large (Fastino)](https://modelscale.dev/models/gliner2-large) - [GLiNER2 large (Fastino) (Fastino)](https://modelscale.dev/models/jevbench-gliner2-large) - [GLiNER2.5 base (Fastino)](https://modelscale.dev/models/gliner2-5-base) - [GLiNER2.5 multi (Fastino)](https://modelscale.dev/models/gliner2-5-multi) - [GLiNER2.5 multi (Fastino, 287M) (Fastino)](https://modelscale.dev/models/jevbench-gliner2-5-multi) - [GLiNER2.5 small (Fastino)](https://modelscale.dev/models/gliner2-5-small) - [GLiNER2.5 small (Fastino, 74M) (Fastino)](https://modelscale.dev/models/jevbench-gliner2-5-small) - [GLiNER2.5-Decide (fastino)](https://modelscale.dev/models/decision-index-0-3-gliner2-5-decide) - [GLM 5.3 FlashX Legal (Z.AI)](https://modelscale.dev/models/glm-5-3-flashx-legal) - [GLM Realtime Air (Zhipu AI)](https://modelscale.dev/models/glm-realtime-air) - [GLM Realtime Flash (Zhipu AI)](https://modelscale.dev/models/glm-realtime-flash) - [GLM-4-Voice (Zhipu AI)](https://modelscale.dev/models/glm-4-voice) - [GLM-4.6V (Z.AI)](https://modelscale.dev/models/glm-4-6v) - [GLM-4.6V-Flash (Z.AI)](https://modelscale.dev/models/glm-4-6v-flash) - [GNN-TabFact (GNN-TabFact comparison) (TabFact authors)](https://modelscale.dev/models/native-tabfact-gnn-tabfact-maintainer) - [GPT Audio 1.5 (OpenAI)](https://modelscale.dev/models/gpt-audio-1-5) - [GPT Live Transcribe (OpenAI)](https://modelscale.dev/models/gpt-live-transcribe) - [GPT Realtime (OpenAI)](https://modelscale.dev/models/gpt-realtime) - [GPT Realtime 1.5 (OpenAI)](https://modelscale.dev/models/gpt-realtime-1-5) - [GPT Realtime 2 (OpenAI)](https://modelscale.dev/models/gpt-realtime-2) - [GPT Realtime 2.1 (OpenAI)](https://modelscale.dev/models/gpt-realtime-2-1) - [GPT Realtime 2.1 Mini (OpenAI)](https://modelscale.dev/models/gpt-realtime-2-1-mini) - [GPT Realtime mini (OpenAI)](https://modelscale.dev/models/gpt-realtime-mini) - [GPT Transcribe (OpenAI)](https://modelscale.dev/models/gpt-transcribe) - [GPT-3.5-turbo-0613 (RAGTruth generator) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-gpt-3-5-turbo-0613-ragtruth-generator) - [GPT-4-0613 (RAGTruth generator) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-gpt-4-0613-ragtruth-generator) - [GPT-4.5 (OpenAI)](https://modelscale.dev/models/gpt-4-5) - [GPT-4o Audio (OpenAI)](https://modelscale.dev/models/gpt-4o-audio) - [GPT-4o mini Audio (OpenAI)](https://modelscale.dev/models/gpt-4o-mini-audio) - [GPT-4o mini TTS (OpenAI)](https://modelscale.dev/models/gpt-4o-mini-tts) - [GPT-4o Solver (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-gpt-4o-solver) - [GPT-5.6 Cyber (OpenAI)](https://modelscale.dev/models/gpt-5-6-cyber) - [GPT-5.6 Luna (low reasoning effort) (OpenAI)](https://modelscale.dev/models/jevbench-gpt-5-6-luna) - [GPT-5.6 Luna (low) (OpenAI)](https://modelscale.dev/models/gpt-5-6-luna-low) - [GPT-6 Cyber (OpenAI)](https://modelscale.dev/models/gpt-6-cyber) - [GPT-6 Luna (Decisions) (OpenAI)](https://modelscale.dev/models/gpt-6-luna-decisions) - [GPT-6 Luna (default medium reasoning effort) (OpenAI)](https://modelscale.dev/models/jevbench-gpt-6-luna) - [GPT-6 Luna (low reasoning effort) (OpenAI)](https://modelscale.dev/models/jevbench-gpt-6-luna-low) - [GPT-6 Luna (low) (OpenAI)](https://modelscale.dev/models/gpt-6-luna-low) - [GPT-6 Luna (medium) (OpenAI)](https://modelscale.dev/models/gpt-6-luna-medium) - [GPT-6.1 Terra Pro (OpenAI)](https://modelscale.dev/models/gpt-6-1-terra-pro) - [GPT-6.2 Astra Pro (OpenAI)](https://modelscale.dev/models/gpt-6-2-astra-pro) - [GPT-6.2 Luna (OpenAI)](https://modelscale.dev/models/gpt-6-2-luna) - [GPT-6.2 Sol Pro (OpenAI)](https://modelscale.dev/models/gpt-6-2-sol-pro) - [GPT-Live-1 (OpenAI)](https://modelscale.dev/models/gpt-live-1) - [GPT3.5-turbo unk (Belebele zero-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-gpt3-5-turbo-unk-zero-shot) - [Granite 4.2 30B (IBM)](https://modelscale.dev/models/granite-4-2-30b) - [Granite 4.2 3B (IBM)](https://modelscale.dev/models/granite-4-2-3b) - [Granite Speech 5.0 470M TurboCTC (IBM)](https://modelscale.dev/models/granite-speech-5-0-470m-turboctc) - [GRM-Gemma-2B (JudgeBench) (GRM authors)](https://modelscale.dev/models/native-judgebench-grm-gemma-2b) - [Grok 2 (xAI)](https://modelscale.dev/models/grok-2) - [Grok 2 mini (xAI)](https://modelscale.dev/models/grok-2-mini) - [Grok 4.20 Multi-agent (xAI)](https://modelscale.dev/models/grok-4-20-multi-agent-beta) - [Grok 4.7 (xAI)](https://modelscale.dev/models/grok-4-7) - [Grok Build 0.1 (xAI)](https://modelscale.dev/models/grok-build-0-1) - [Grok Realtime (xAI)](https://modelscale.dev/models/grok-realtime) - [Grok TTS (xAI)](https://modelscale.dev/models/grok-tts) - [Grok Voice 3.0 (xAI)](https://modelscale.dev/models/grok-voice-3-0) - [Grok Voice Think Fast 1.0 (xAI)](https://modelscale.dev/models/grok-voice-think-fast-1-0) - [Grok Voice Think Fast 2.0 (xAI)](https://modelscale.dev/models/grok-voice-think-fast-2-0) - [Grok Voice Transcribe 2.0 (xAI)](https://modelscale.dev/models/grok-voice-transcribe-2) - [Hark Handoff (Hark)](https://modelscale.dev/models/hark-handoff) - [Hark Handoff 2 (Hark)](https://modelscale.dev/models/hark-handoff-2) - [HeyGen Decision 1 (HeyGen)](https://modelscale.dev/models/heygen-decision-1) - [HeyGen Decision 1 Turbo (HeyGen)](https://modelscale.dev/models/heygen-decision-1-turbo) - [HeyGen Voice (HeyGen)](https://modelscale.dev/models/heygen-voice) - [Holo2-235B-A22B (H Company)](https://modelscale.dev/models/holo2-235b-a22b) - [Holo2-30B-A3B (H Company)](https://modelscale.dev/models/holo2-30b-a3b) - [Holo2-4B (H Company)](https://modelscale.dev/models/holo2-4b) - [Holo2-8B (H Company)](https://modelscale.dev/models/holo2-8b) - [Holo3-122B-A10B (H Company)](https://modelscale.dev/models/holo3-122b-a10b) - [Holo3-35B-A3B (H Company)](https://modelscale.dev/models/holo3-35b-a3b) - [Holo3.1-0.8B (H Company)](https://modelscale.dev/models/holo3-1-0-8b) - [Holo3.1-35B-A3B (H Company)](https://modelscale.dev/models/holo3-1-35b-a3b) - [Holo3.1-35B-A3B-FP8 (H Company)](https://modelscale.dev/models/holo3-1-35b-a3b-fp8) - [Holo3.1-35B-A3B-GGUF (H Company)](https://modelscale.dev/models/holo3-1-35b-a3b-gguf) - [Holo3.1-35B-A3B-NVFP4 (H Company)](https://modelscale.dev/models/holo3-1-35b-a3b-nvfp4) - [Holo3.1-4B (H Company)](https://modelscale.dev/models/holo3-1-4b) - [Holo3.1-9B (H Company)](https://modelscale.dev/models/holo3-1-9b) - [Holotron-12B (H Company)](https://modelscale.dev/models/holotron-12b) - [Hopper (HopitAI)](https://modelscale.dev/models/hopper) - [Hopper (HopitAI)](https://modelscale.dev/models/jevbench-hopper) - [Hopper (G) 1.2 (HopitAI)](https://modelscale.dev/models/decision-index-0-3-hopper-g-1-2) - [Hopper 12B (trained) (Not listed)](https://modelscale.dev/models/decision-index-0-3-hopper-12b-trained) - [Hy ASR 3.0 preview (Tencent)](https://modelscale.dev/models/hy-asr-3-0-preview) - [Hy-Memory-30B-A3B (Tencent)](https://modelscale.dev/models/hy-memory-30b-a3b) - [Hy-MT1.5-1.8B-1.25bit (Tencent Hunyuan)](https://modelscale.dev/models/hy-mt1-5-1-8b-1-25bit) - [Hy-MT2-1.8B (Tencent)](https://modelscale.dev/models/hy-mt2-1-8b) - [Hy-MT2-30B-A3B (Tencent)](https://modelscale.dev/models/hy-mt2-30b-a3b) - [Hy4 flash (Tencent)](https://modelscale.dev/models/hy4-flash) - [HyperClova X Dash (Naver Cloud)](https://modelscale.dev/models/hyperclova-x-dash) - [HyperClova X Think 32B (Naver Cloud)](https://modelscale.dev/models/hyperclova-x-think) - [Ichigo (Jan)](https://modelscale.dev/models/ichigo) - [Imajev-4B (mohit67890)](https://modelscale.dev/models/imajev-4b) - [Imajev-4B (mohit67890)](https://modelscale.dev/models/jevbench-imajev-4b) - [Imajev-4B (RTX 5090) (mohit67890)](https://modelscale.dev/models/imajev-4b-rtx5090-a2) - [Imajev-4B (RTX 5090) (unknown)](https://modelscale.dev/models/jevbench-imajev-4b-rtx5090-a2) - [InfoXLM large (550M) (Belebele English fine-tuning) (Belebele authors)](https://modelscale.dev/models/native-belebele-infoxlm-large-550m-english-fine-tuning) - [InfoXLM large (550M) (Belebele Translate-Train-All) (Belebele authors)](https://modelscale.dev/models/native-belebele-infoxlm-large-550m-translate-train-all) - [Instinct (ZooWork, Qwen3.8-27B) (rayrain-srp (ZooWork))](https://modelscale.dev/models/jevbench-instinct) - [Instinct Dual 4B (ZooWork)](https://modelscale.dev/models/instinct-dual-4b) - [Instinct Dual 4B (ZooWork / pierre-srp)](https://modelscale.dev/models/jevbench-instinct-dual-4b) - [Instinct Qwen3.8-27B (ZooWork)](https://modelscale.dev/models/instinct) - [Intelif Qwen3-4B (Not listed)](https://modelscale.dev/models/decision-index-0-3-intelif-qwen3-4b) - [Interfaze Beta (Interfaze)](https://modelscale.dev/models/interfaze-beta) - [Intern-Decision-0.8B (internlm)](https://modelscale.dev/models/decision-index-0-3-intern-decision-0-8b) - [Intern-Decision-2B (internlm)](https://modelscale.dev/models/decision-index-0-3-intern-decision-2b) - [Intern-Decision-4B (internlm)](https://modelscale.dev/models/decision-index-0-3-intern-decision-4b) - [InternLM2-20B-Reward (JudgeBench) (InternLM)](https://modelscale.dev/models/native-judgebench-internlm2-20b-reward) - [InternLM2-7B-Reward (JudgeBench) (InternLM)](https://modelscale.dev/models/native-judgebench-internlm2-7b-reward) - [Inworld Realtime TTS-2 (Inworld)](https://modelscale.dev/models/inworld-tts-2) - [Inworld Realtime TTS-2 Flash (Inworld)](https://modelscale.dev/models/inworld-tts-2-flash) - [Inworld TTS-1.5 Max (Inworld)](https://modelscale.dev/models/inworld-tts-1-5-max) - [JADE (Not listed)](https://modelscale.dev/models/decision-index-0-3-jade) - [Jais-3-0.9B (IFM)](https://modelscale.dev/models/jais-3-0-9b) - [Jais-3-0.9B-Uno (IFM)](https://modelscale.dev/models/jais-3-0-9b-uno) - [Jais-3-3.7B (IFM)](https://modelscale.dev/models/jais-3-3-7b) - [Jais-3-3.7B-Uno (IFM)](https://modelscale.dev/models/jais-3-3-7b-uno) - [Jais-3-32B (IFM)](https://modelscale.dev/models/jais-3-32b) - [Jais-3-32B-Uno (IFM)](https://modelscale.dev/models/jais-3-32b-uno) - [Jais-3-375B-A23B (IFM)](https://modelscale.dev/models/jais-3-375b-a23b) - [Jais-3-7B (IFM)](https://modelscale.dev/models/jais-3-7b) - [Jais-3-7B-Uno (IFM)](https://modelscale.dev/models/jais-3-7b-uno) - [Jais-3-MoVA-36B-A4B (IFM)](https://modelscale.dev/models/jais-3-mova-36b-a4b) - [Jais-ASR (IFM)](https://modelscale.dev/models/jais-asr) - [Jebadiah 27B (frontier-infra)](https://modelscale.dev/models/decision-index-0-3-jebadiah-27b) - [jeff (Logan Markewich)](https://modelscale.dev/models/jeff) - [jeff (Logan Markewich, GLiFormer 400M) (Logan Markewich)](https://modelscale.dev/models/jevbench-jeff) - [Jet v6.2 (michaljach)](https://modelscale.dev/models/decision-index-0-3-jet-v6-2) - [Jev (Not listed)](https://modelscale.dev/models/decision-index-0-3-jev) - [Jev 1.13.0 (TypeSafe AI)](https://modelscale.dev/models/jev-1-13-0) - [Jev 1.13.0 (TypeSafe AI) (TypeSafe AI)](https://modelscale.dev/models/jevbench-jev-1-13-0) - [Jev 1.14 (TypeSafe AI)](https://modelscale.dev/models/jev-1-14) - [JEV Qwen3.5-9B Base NVFP4 (WilfLin)](https://modelscale.dev/models/jev-qwen3-5-9b-base-nvfp4) - [JEV Qwen3.5-9B Base NVFP4 (WilfLin)](https://modelscale.dev/models/jevbench-jev-qwen3-5-9b-base-nvfp4) - [JEV-27B (autotrust)](https://modelscale.dev/models/decision-index-0-3-jev-27b) - [JEV-9B (autotrust)](https://modelscale.dev/models/decision-index-0-3-jev-9b) - [jev-local (Qwen3.5-9B) (us (GitHub))](https://modelscale.dev/models/jevbench-jev-local) - [jev-local Qwen3.5-9B (us (GitHub))](https://modelscale.dev/models/jev-local) - [Jev-Omni (akhilaaa3)](https://modelscale.dev/models/jev-omni) - [Jev-Omni (akhilaaa3, Gemma-4-12B merged) (akhilaaa3)](https://modelscale.dev/models/jevbench-jev-omni) - [Jev-Style 0.8B v3 (Not listed)](https://modelscale.dev/models/decision-index-0-3-jev-style-0-8b-v3) - [Jev-Style 2B v3 (Not listed)](https://modelscale.dev/models/decision-index-0-3-jev-style-2b-v3) - [JevAct (einptein)](https://modelscale.dev/models/jevact) - [JevAct (einptein, jev1-2b-v2) (einptein)](https://modelscale.dev/models/jevbench-jevact) - [Jevfire (Not listed)](https://modelscale.dev/models/decision-index-0-3-jevfire) - [JevK5 9B v0.3.3 (alibiserikbay)](https://modelscale.dev/models/decision-index-0-3-jevk5-9b-v0-3-3) - [JevK5 Lite (alibiserikbay)](https://modelscale.dev/models/decision-index-0-3-jevk5-lite) - [JevK5 v0.2.0 (allebee)](https://modelscale.dev/models/jevbench-jevk5-v02) - [JevK5 v0.2.0 (allebee)](https://modelscale.dev/models/jevk5-v0-2-0) - [JevK5 v0.3 (Not listed)](https://modelscale.dev/models/decision-index-0-3-jevk5-v0-3) - [JevK5 v0.3 (4B) (unknown)](https://modelscale.dev/models/jevbench-jevk5-v0-3-4b) - [JevK5 v0.3 4B (allebee)](https://modelscale.dev/models/jevk5-v0-3-4b) - [JevOne (Juspay)](https://modelscale.dev/models/jevbench-jevone) - [JevOne (Juspay)](https://modelscale.dev/models/jevone) - [Jevstral 8B (AmirBraham)](https://modelscale.dev/models/decision-index-0-3-jevstral-8b) - [jiwo 0.8B (eljiwo)](https://modelscale.dev/models/decision-index-0-3-jiwo-0-8b) - [jiwo 4B (eljiwo)](https://modelscale.dev/models/decision-index-0-3-jiwo-4b) - [Jobe (Not listed)](https://modelscale.dev/models/decision-index-0-3-jobe) - [Jobe Qwen3.5-4B (MantisShrimpdev)](https://modelscale.dev/models/jobe-qwen3-5-4b) - [Jobe Qwen3.5-4B (frozen) (MantisShrimpdev)](https://modelscale.dev/models/jevbench-jobe-qwen3-5-4b) - [JoshuaSP diffusiongemma (open-jev) (Not listed)](https://modelscale.dev/models/decision-index-0-3-joshuasp-diffusiongemma-open-jev) - [JPT-0.8B (kirp)](https://modelscale.dev/models/decision-index-0-3-jpt-0-8b) - [JPT-35B-A3B (kirp)](https://modelscale.dev/models/decision-index-0-3-jpt-35b-a3b) - [JPT-4B (kirp)](https://modelscale.dev/models/decision-index-0-3-jpt-4b) - [JPT-9B (kirp)](https://modelscale.dev/models/decision-index-0-3-jpt-9b) - [jqv (Qwen3-32B zero-shot) (hjmurmur (Octalab))](https://modelscale.dev/models/jevbench-jqv) - [jqv Qwen3-32B (Octalab)](https://modelscale.dev/models/jqv) - [JudgeLM-13B-v1.0 (JudgeBench) (BAAI)](https://modelscale.dev/models/native-judgebench-judgelm-13b-v1-0) - [JudgeLM-33B-v1.0 (JudgeBench) (BAAI)](https://modelscale.dev/models/native-judgebench-judgelm-33b-v1-0) - [JudgeLM-7B-v1.0 (JudgeBench) (BAAI)](https://modelscale.dev/models/native-judgebench-judgelm-7b-v1-0) - [Julia 1 (SupersonicLabs)](https://modelscale.dev/models/decision-index-0-3-julia-1) - [K-Exaone (LG AI Research)](https://modelscale.dev/models/k-exaone) - [K-EXAONE 2.0 (LG AI Research)](https://modelscale.dev/models/k-exaone-2-0) - [Kalpa TTS Beta v0.1 (Kalpa Labs)](https://modelscale.dev/models/kalpa-tts-beta-v0-1) - [Kanana Essence (Kakao)](https://modelscale.dev/models/kanana-essence) - [Kanana Flag (Kakao)](https://modelscale.dev/models/kanana-flag) - [Kanana Nano (Kakao)](https://modelscale.dev/models/kanana-nano) - [Kanana-2 1.3B Instruct (Kakao)](https://modelscale.dev/models/kanana-2-1-3b-instruct) - [Kanana-2 3B Instruct (Kakao)](https://modelscale.dev/models/kanana-2-3b-instruct) - [Kas 4B (kpiya)](https://modelscale.dev/models/decision-index-0-3-kas-4b) - [kev 0.5B (Jared Palmer)](https://modelscale.dev/models/jevbench-kev-0-5b) - [kev 0.5B (Jared Palmer)](https://modelscale.dev/models/kev-0-5b) - [kev 0.6B (Jared Palmer)](https://modelscale.dev/models/kev-0-6b) - [kev 0.6B (research preview) (Jared Palmer)](https://modelscale.dev/models/jevbench-kev-0-6b) - [Kev 0.8B r15 (Not listed)](https://modelscale.dev/models/decision-index-0-3-kev-0-8b-r15) - [Kev 27B (jaredpalmer)](https://modelscale.dev/models/decision-index-0-3-kev-27b) - [kev 4B (Jared Palmer)](https://modelscale.dev/models/kev-4b) - [kev 4B (research preview) (Jared Palmer)](https://modelscale.dev/models/jevbench-kev-4b) - [Kev 4B r10 (jaredpalmer)](https://modelscale.dev/models/decision-index-0-3-kev-4b-r10) - [kev 8B (Jared Palmer)](https://modelscale.dev/models/kev-8b) - [kev 8B (research preview) (Jared Palmer)](https://modelscale.dev/models/jevbench-kev-8b) - [Kev 9B v2 (Not listed)](https://modelscale.dev/models/decision-index-0-3-kev-9b-v2) - [Kimi K3.1 Pro Highspeed (Moonshot AI)](https://modelscale.dev/models/kimi-k3-1-pro-highspeed) - [Kimi-Audio 7B (Moonshot AI)](https://modelscale.dev/models/kimi-audio-7b) - [Kodiak v0.2 1B (accuracy) (cortex-agent-llc)](https://modelscale.dev/models/decision-index-0-3-kodiak-v0-2-1b-accuracy) - [Kokoro 82M (hexgrad)](https://modelscale.dev/models/kokoro-82m) - [Kyutai Pocket TTS (Kyutai)](https://modelscale.dev/models/kyutai-pocket-tts) - [Laguna XS 2.1 (Poolside)](https://modelscale.dev/models/laguna-xs-2-1) - [Lavoir (moganai)](https://modelscale.dev/models/decision-index-0-3-lavoir) - [Laya (Convai Innovations)](https://modelscale.dev/models/laya) - [Laya (Convai Innovations, ModernBERT-large 421M) (Convai Innovations)](https://modelscale.dev/models/jevbench-laya) - [Laya multilingual (Convai Innovations)](https://modelscale.dev/models/jevbench-laya-multilingual) - [Laya multilingual (Convai Innovations)](https://modelscale.dev/models/laya-multilingual) - [Laya typed-decisions (Convai Innovations)](https://modelscale.dev/models/jevbench-laya-typed-decisions) - [Laya typed-decisions (Convai Innovations)](https://modelscale.dev/models/laya-typed-decisions) - [Leanstral (Mistral)](https://modelscale.dev/models/leanstral) - [Leanstral 1.5 (Mistral)](https://modelscale.dev/models/leanstral-1-5) - [lev (interfaze-ai)](https://modelscale.dev/models/decision-index-0-3-lev) - [lev-350m (Franck Verrot (franckverrot))](https://modelscale.dev/models/lev-350m) - [lev-350m (Franck Verrot, LFM2.5-350M) (Franck Verrot (franckverrot))](https://modelscale.dev/models/jevbench-lev-350m) - [Lev1 3.7B (Not listed)](https://modelscale.dev/models/decision-index-0-3-lev1-3-7b) - [LFG-1 (glenn2)](https://modelscale.dev/models/lfg-1) - [LFG-2 (glenn2)](https://modelscale.dev/models/lfg-2) - [LFG-3 (glenn2)](https://modelscale.dev/models/lfg-3) - [LFM2.5-1.2B-JP-202606 (LiquidAI)](https://modelscale.dev/models/lfm2-5-1-2b-jp-202606) - [LFM2.5-2.6B-RLCD (monotykamary)](https://modelscale.dev/models/decision-index-0-3-lfm2-5-2-6b-rlcd) - [LFM2.5-230M (LiquidAI)](https://modelscale.dev/models/lfm2-5-230m) - [LFM2.5-350M (LiquidAI)](https://modelscale.dev/models/lfm2-5-350m) - [LFM2.5-350M-RLCD (notnotsamuel)](https://modelscale.dev/models/decision-index-0-3-lfm2-5-350m-rlcd) - [LFM2.5-ColBERT-350M (LiquidAI)](https://modelscale.dev/models/lfm2-5-colbert-350m) - [LFM2.5-Embedding-350M (LiquidAI)](https://modelscale.dev/models/lfm2-5-embedding-350m) - [LFM2.5-VL-1.6B-Extract (LiquidAI)](https://modelscale.dev/models/lfm2-5-vl-1-6b-extract) - [LFM2.5-VL-3B (LiquidAI)](https://modelscale.dev/models/lfm2-5-vl-3b) - [LFM2.5-VL-450M (LiquidAI)](https://modelscale.dev/models/lfm2-5-vl-450m) - [LFM2.5-VL-450M-Extract (LiquidAI)](https://modelscale.dev/models/lfm2-5-vl-450m-extract) - [LFM3-1.7B-Base (LiquidAI)](https://modelscale.dev/models/lfm3-1-7b-base) - [LFM3-Audio-2B (LiquidAI)](https://modelscale.dev/models/lfm3-audio-2b) - [LFM3-Omni-2B (LiquidAI)](https://modelscale.dev/models/lfm3-omni-2b) - [LFM3-VL-2B (LiquidAI)](https://modelscale.dev/models/lfm3-vl-2b) - [Lightning v3.1 Pro (Smallest AI)](https://modelscale.dev/models/lightning-v3-1-pro) - [Ling 3.0 Flash Fin (InclusionAI)](https://modelscale.dev/models/ling-3-0-flash-fin) - [Ling 3.0 Flash FP8 (InclusionAI)](https://modelscale.dev/models/ling-3-0-flash-fp8) - [Ling 3.0 Flash Sante (InclusionAI)](https://modelscale.dev/models/ling-3-0-flash-sante) - [Ling 3.0 Tiny (InclusionAI)](https://modelscale.dev/models/ling-3-0-tiny) - [LitJev (Qwen3.8-27B) (Zhengxu Yu)](https://modelscale.dev/models/jevbench-litjev) - [LitJev Qwen3.8-27B (Zhengxu Yu)](https://modelscale.dev/models/litjev) - [LLaDA2.2-flash (InclusionAI)](https://modelscale.dev/models/llada2-2-flash) - [LLaDA2.2-mini (InclusionAI)](https://modelscale.dev/models/llada2-2-mini) - [Llama 1 13B (Belebele 5-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-1-13b-5-shot) - [Llama 1 30B (Belebele 5-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-1-30b-5-shot) - [Llama 1 65B (Belebele 5-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-1-65b-5-shot) - [Llama 1 7B (Belebele 5-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-1-7b-5-shot) - [Llama 2 base 70B (Belebele 5-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-base-70b-5-shot) - [Llama 3.1 70B (Meta)](https://modelscale.dev/models/llama-3-1-70b) - [Llama 3.1 8B (Meta)](https://modelscale.dev/models/llama-3-1-8b) - [Llama 3.3 70B (Meta)](https://modelscale.dev/models/llama-3-3-70b) - [Llama-2-13B-chat (RAGTruth generator) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-llama-2-13b-chat-ragtruth-generator) - [Llama-2-70B-chat (RAGTruth, 4-bit) (Meta / TheBloke)](https://modelscale.dev/models/native-ragtruth-llama-2-70b-chat-ragtruth-4-bit) - [Llama-2-7B-chat (RAGTruth generator) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-llama-2-7b-chat-ragtruth-generator) - [Llama-2-chat 70B (Belebele 89-language English instructions) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-chat-70b-89-language-english-instructions) - [Llama-2-chat 70B (Belebele 89-language translated instructions) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-chat-70b-89-language-translated-instructions) - [Llama-2-chat 70B (Belebele 91-language in-language) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-chat-70b-91-language-in-language) - [Llama-2-chat 70B (Belebele 91-language Translate-Test) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-chat-70b-91-language-translate-test) - [Llama-2-chat 70B (Belebele zero-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-chat-70b-zero-shot) - [Llama-2-chat 7B (Belebele zero-shot) (Belebele authors)](https://modelscale.dev/models/native-belebele-llama-2-chat-7b-zero-shot) - [Llama-3.1-405B-Instruct Solver (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-llama-3-1-405b-instruct-solver) - [Llama-3.1-Nemotron-70B-Reward (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-1-nemotron-70b-reward) - [Llama-3.3-Nemotron-70B-Reward (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-70b-reward) - [Llama-3.3-Nemotron-70B-Reward-Multilingual (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-70b-reward-multilingual) - [Llama-3.3-Nemotron-70B-Reward-Principle (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-70b-reward-principle) - [Llama-3.3-Nemotron-Super-49B-GenRM (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-super-49b-genrm) - [Llama-3.3-Nemotron-Super-49B-GenRM + voting@32 (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-super-49b-genrm-voting-32) - [Llama-3.3-Nemotron-Super-49B-GenRM-Multilingual (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-super-49b-genrm-multilingual) - [Llama-3.3-Nemotron-Super-49B-GenRM-Multilingual + voting@32 (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-llama-3-3-nemotron-super-49b-genrm-multilingual-voting-32) - [LLaMA-Omni (ICTNLP)](https://modelscale.dev/models/llama-omni) - [LMvLM (gpt-4-turbo) (RAGTruth detector) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-lmvlm-gpt-4-turbo-detector) - [local-jev Qwen3.5-4B (Amith Chandrappa (amithgc))](https://modelscale.dev/models/jevbench-localjev-qwen3-5-4b) - [local-jev Qwen3.5-4B (Amith Chandrappa (amithgc))](https://modelscale.dev/models/localjev-qwen3-5-4b) - [LongCat-2.0 (Meituan)](https://modelscale.dev/models/longcat-2-0) - [LongCat-2.5 (Meituan)](https://modelscale.dev/models/longcat-2-5) - [LongCat-Flash-Lite-Sparse (Meituan)](https://modelscale.dev/models/longcat-flash-lite-sparse) - [LPA-Ranking w/ Discriminator (Caption) (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-lpa-ranking-w-discriminator-caption) - [LPA-Ranking w/ Discriminator (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-lpa-ranking-w-discriminator) - [LPA-Voting w/o Discriminator (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-lpa-voting-w-o-discriminator) - [LPA-Weighted-Voting (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-lpa-weighted-voting) - [LPS (FinancialPhraseBank) (Malo et al.)](https://modelscale.dev/models/native-financialphrasebank-lps) - [Lyra Base (DVL Lab)](https://modelscale.dev/models/lyra-base) - [Lyra Mini (DVL Lab)](https://modelscale.dev/models/lyra-mini) - [Macaw (Bad Theory Labs)](https://modelscale.dev/models/macaw-v1) - [Magistral Medium (Mistral)](https://modelscale.dev/models/magistral-medium) - [Magistral Small (Mistral)](https://modelscale.dev/models/magistral-small) - [MAI Code 2 (Microsoft)](https://modelscale.dev/models/mai-code-2) - [MAI Code 2 Flash (Microsoft)](https://modelscale.dev/models/mai-code-2-flash) - [MAI-Code-1.1-Flash (Microsoft)](https://modelscale.dev/models/mai-code-1-1-flash) - [MAI-Cyber-1-Flash (Microsoft)](https://modelscale.dev/models/mai-cyber-1-flash) - [MAI-Transcribe-1.5 (Microsoft)](https://modelscale.dev/models/mai-transcribe-1-5) - [MAI-Transcribe-2 (Microsoft)](https://modelscale.dev/models/mai-transcribe-2) - [MAI-Transcribe-2-Streaming (Microsoft)](https://modelscale.dev/models/mai-transcribe-2-streaming) - [MAI-Voice-2 (Microsoft)](https://modelscale.dev/models/mai-voice-2) - [MAI-Voice-2-Flash (Microsoft)](https://modelscale.dev/models/mai-voice-2-flash) - [MAI-Voice-2.1 (Microsoft)](https://modelscale.dev/models/mai-voice-2-1) - [MAI-Voice-2.1-Flash (Microsoft)](https://modelscale.dev/models/mai-voice-2-1-flash) - [Mair-hub 0.5B Omni (Mair Hub)](https://modelscale.dev/models/mair-hub-0-5b-omni) - [Malkuth-2B (newfull5 (dhtocks))](https://modelscale.dev/models/malkuth-2b) - [Malkuth-2B (newfull5, Kev post-train) (newfull5 (dhtocks))](https://modelscale.dev/models/jevbench-malkuth-2b) - [Malkuth-4B (newfull5 (dhtocks))](https://modelscale.dev/models/malkuth-4b) - [Malkuth-4B (newfull5, Kev post-train) (newfull5 (dhtocks))](https://modelscale.dev/models/jevbench-malkuth-4b) - [mammoth-1 (Baseten)](https://modelscale.dev/models/mammoth-1) - [Manchego v2.1 (oraculumai)](https://modelscale.dev/models/jevbench-manchego-v21-v15) - [Manchego v2.1 (oraculumai)](https://modelscale.dev/models/manchego-v2-1) - [Megrez-3B-Omni (Infinigence AI)](https://modelscale.dev/models/megrez-3b-omni) - [Mellum2-12B-A2.5B-Instruct (JetBrains)](https://modelscale.dev/models/mellum2-12b-a2-5b-instruct) - [Mellum2-12B-A2.5B-Thinking (JetBrains)](https://modelscale.dev/models/mellum2-12b-a2-5b-thinking) - [Mellum2.1-12B-A2.5B-Thinking (JetBrains)](https://modelscale.dev/models/mellum2-1-12b-a2-5b-thinking) - [MERaLiON-AudioLLM (AI Singapore)](https://modelscale.dev/models/meralion-audiollm) - [Mercury 2.5 Preview (Inception)](https://modelscale.dev/models/mercury-2-5-preview) - [Mercury 3 (Inception)](https://modelscale.dev/models/mercury-3) - [Mercury Decide (Inception)](https://modelscale.dev/models/mercury-decide) - [Mercury Edit 2 (Inception)](https://modelscale.dev/models/mercury-edit-2) - [Mercury Voice (Inception)](https://modelscale.dev/models/mercury-voice) - [metask-jev-4b (Wayfind (metask-ai))](https://modelscale.dev/models/jevbench-metask-jev-4b) - [metask-jev-4b (Wayfind (metask-ai))](https://modelscale.dev/models/metask-jev-4b) - [Mica v0.1 4B (sky7350)](https://modelscale.dev/models/mica-v0-1-4b) - [mica-v01-4b (unknown)](https://modelscale.dev/models/jevbench-mica-v01-4b) - [Microsoft-Decision-1 (Microsoft)](https://modelscale.dev/models/microsoft-decision-1) - [Ming-3.0-asr-tiny (InclusionAI)](https://modelscale.dev/models/ming-3-0-asr-tiny) - [Ming-3.0-audio-flash (InclusionAI)](https://modelscale.dev/models/ming-3-0-audio-flash) - [Ming-3.0-audio-tiny (InclusionAI)](https://modelscale.dev/models/ming-3-0-audio-tiny) - [Ming-3.0-tts-0.5B (InclusionAI)](https://modelscale.dev/models/ming-3-0-tts-0-5b) - [Ming-3.0-tts-tiny (InclusionAI)](https://modelscale.dev/models/ming-3-0-tts-tiny) - [mini-jev (Not listed)](https://modelscale.dev/models/decision-index-0-3-mini-jev) - [Mini-Omni 0.5B (gpt-omni)](https://modelscale.dev/models/mini-omni) - [Mini-Omni2 (gpt-omni)](https://modelscale.dev/models/mini-omni2) - [MiniCPM-o 2.6 (OpenBMB)](https://modelscale.dev/models/minicpm-o-2-6) - [MiniCPM5-2B (OpenBMB)](https://modelscale.dev/models/minicpm5-2b) - [MiniMax M3.1 Flash Preview (MiniMax)](https://modelscale.dev/models/minimax-m3-1-flash-preview) - [MiniMax Speech 2.8 HD (MiniMax)](https://modelscale.dev/models/minimax-speech-2-8-hd) - [MiniMax Speech-02 HD (MiniMax)](https://modelscale.dev/models/minimax-speech-02-hd) - [MiniMax-Text-01 (MiniMax)](https://modelscale.dev/models/minimax-text-01) - [MiniMax-VL-01 (MiniMax)](https://modelscale.dev/models/minimax-vl-01) - [Mirror (Bluusun)](https://modelscale.dev/models/jevbench-mirror) - [Mirror (Bluusun)](https://modelscale.dev/models/mirror) - [Mistral Small 3.1 (Mistral)](https://modelscale.dev/models/mistral-small-3-1) - [Mistral Small 4 (Reasoning) (Mistral)](https://modelscale.dev/models/mistral-small-4-reasoning) - [Mistral-7B-Instruct (RAGTruth generator) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-mistral-7b-instruct-ragtruth-generator) - [Mixedbread mxbai-rerank-base-v2 (Mixedbread)](https://modelscale.dev/models/jevbench-mxbai-rerank-base-v2) - [Mixedbread mxbai-rerank-base-v2 (Mixedbread)](https://modelscale.dev/models/mxbai-rerank-base-v2) - [mmastrac diffusiongemma (vLLM PR 57250) (Not listed)](https://modelscale.dev/models/decision-index-0-3-mmastrac-diffusiongemma-vllm-pr-57250) - [MNLI (Circa) (Louis et al.)](https://modelscale.dev/models/native-circa-mnli) - [Moonshine Tiny (Useful Sensors)](https://modelscale.dev/models/moonshine-tiny) - [Moshi 7B (Kyutai)](https://modelscale.dev/models/moshi-7b) - [Murf Falcon 2 (Murf AI)](https://modelscale.dev/models/murf-falcon-2) - [Muse Spark 1.3 (Meta)](https://modelscale.dev/models/muse-spark-1-3) - [Muse Voice Transcribe (Meta)](https://modelscale.dev/models/muse-voice-transcribe) - [Nano Banana 2.1 (Google)](https://modelscale.dev/models/gemini-nano-banana-2-1) - [Needle 3 (2-bit) (Cactus Compute)](https://modelscale.dev/models/needle-3) - [Needle 3 (Cactus, 2-bit, local CPU) (Cactus Compute)](https://modelscale.dev/models/jevbench-needle-3) - [Needle 3 (options as tools) (Cactus Compute)](https://modelscale.dev/models/needle-3-tools) - [Needle 3, options as tools (post-hoc adapter mode) (Cactus Compute)](https://modelscale.dev/models/jevbench-needle-3-tools) - [Nemotron 3.5 ASR Streaming 0.6B (NVIDIA)](https://modelscale.dev/models/nemotron-3-5-asr-streaming-0-6b) - [Nemotron 3.5 Bolt 74B-A9B BF16 (NVIDIA)](https://modelscale.dev/models/nemotron-3-5-bolt-74b-a9b-bf16) - [Nemotron 3.5 Bolt E4B (NVIDIA)](https://modelscale.dev/models/nemotron-3-5-bolt-e4b) - [Nemotron 3.5 Bolt E4B BF16 (NVIDIA)](https://modelscale.dev/models/nemotron-3-5-bolt-e4b-bf16) - [Nemotron 3.5 Super VL 120B A12B NVFP4 (NVIDIA)](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b-nvfp4) - [Nemotron 3.5 Transcribe 30B A4B (NVIDIA)](https://modelscale.dev/models/nemotron-3-5-transcribe-30b-a4b) - [Nemotron Diffusion 8B (optimized vLLM) (pst2154)](https://modelscale.dev/models/nemotron-diffusion-8b) - [Nemotron Diffusion 8B (pst2154, optimized vLLM) (pst2154)](https://modelscale.dev/models/jevbench-nemotron-diffusion-8b) - [NeoHorse-Jev-4B (TokenRhythm)](https://modelscale.dev/models/decision-index-0-3-neohorse-jev-4b) - [NExT-GPT 7B (NExT-GPT authors)](https://modelscale.dev/models/next-gpt-7b) - [NInfer Qwen3.8-27B NVFP4 (Igor L. / NInfer contributors)](https://modelscale.dev/models/jevbench-ninfer-qwen3-8-27b) - [NInfer Qwen3.8-27B NVFP4 (Igor L. / NInfer contributors)](https://modelscale.dev/models/ninfer-qwen3-8-27b) - [NInfer Qwen3.8-27B NVFP4 (T=1.5) (Igor L. / NInfer contributors)](https://modelscale.dev/models/jevbench-ninfer-qwen3-8-27b-t1-5) - [NInfer Qwen3.8-27B NVFP4 (T=1.5) (Igor L. / NInfer contributors)](https://modelscale.dev/models/ninfer-qwen3-8-27b-t1-5) - [NInfer Qwen3.8-Flash-Next mixed (Igor L. / NInfer contributors)](https://modelscale.dev/models/jevbench-ninfer-qwen3-8-flash-next) - [NInfer Qwen3.8-Flash-Next mixed (Igor L. / NInfer contributors)](https://modelscale.dev/models/ninfer-qwen3-8-flash-next) - [North Micro Vision Instruct (Cohere)](https://modelscale.dev/models/north-micro-vision-instruct) - [North Mini Code (Cohere)](https://modelscale.dev/models/north-mini-code-1-0) - [North Small Translate (Cohere)](https://modelscale.dev/models/north-small-translate-1-0) - [NSM w/ LPA-guided ML + RL (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-nsm-w-lpa-guided-ml-rl) - [NSM w/ RL (Binary Reward) (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-nsm-w-rl-binary-reward) - [o1-mini (OpenAI)](https://modelscale.dev/models/o1-mini) - [o4-mini (OpenAI)](https://modelscale.dev/models/o4-mini) - [Ola (Ola-Omni)](https://modelscale.dev/models/ola-omni) - [Olala mini 7A1B (OVHcloud)](https://modelscale.dev/models/olala-mini-7a1b) - [OneJev 0.8B (OmniJev)](https://modelscale.dev/models/decision-index-0-3-onejev-0-8b) - [Open Jev JSON Canvas (JoshuaSP)](https://modelscale.dev/models/open-jev-json-canvas-joshuasp) - [Open Jev JSON Canvas (JoshuaSP) (JoshuaSP)](https://modelscale.dev/models/jevbench-open-jev-json-canvas-joshuasp) - [open-alternative-jev (Qwen3.5-4B, IkerMoel) (IkerMoel)](https://modelscale.dev/models/jevbench-open-alternative-jev) - [open-alternative-jev Qwen3.5-4B (IkerMoel)](https://modelscale.dev/models/open-alternative-jev) - [open-jev (pngwn) (Not listed)](https://modelscale.dev/models/decision-index-0-3-open-jev-pngwn) - [Open-Jev 2B (Zefan Cai (@Zefan_Cai))](https://modelscale.dev/models/open-jev-zefan-2b) - [Open-Jev 2B (Zefan Cai) (Zefan Cai (@Zefan_Cai))](https://modelscale.dev/models/jevbench-open-jev-zefan-2b) - [Open-Jev 9B (Zefan Cai (@Zefan_Cai))](https://modelscale.dev/models/open-jev-zefan-9b) - [Open-Jev 9B (Zefan Cai) (Zefan Cai (@Zefan_Cai))](https://modelscale.dev/models/jevbench-open-jev-zefan-9b) - [open-jev-deberta-v3-large (Kotoba Labs)](https://modelscale.dev/models/open-jev-deberta-v3-large) - [open-jev-deberta-v3-large (local CPU) (Kotoba Labs)](https://modelscale.dev/models/jevbench-open-jev-deberta-v3-large) - [OpenDecision (ModernBERT-large zero-shot) (Deepan Wadhwa)](https://modelscale.dev/models/jevbench-opendecision) - [OpenDecision ModernBERT-large (Deepan Wadhwa)](https://modelscale.dev/models/opendecision) - [OpenJev (razorback16)](https://modelscale.dev/models/openjev) - [OpenJev (DiffusionGemma 26B-A4B NVFP4, razorback16) (razorback16 / Codiv)](https://modelscale.dev/models/jevbench-openjev-razorback16) - [OpenJev (thinking, BF16) (razorback16)](https://modelscale.dev/models/jevbench-openjev-thinking) - [OpenJev (thinking, BF16) (razorback16)](https://modelscale.dev/models/openjev-thinking) - [OpenJev DiffusionGemma 26B-A4B NVFP4 (razorback16 / Codiv)](https://modelscale.dev/models/openjev-razorback16) - [openJev Verdict (Hemant (heman10x))](https://modelscale.dev/models/openjev-verdict) - [openJev Verdict (heman10x, ModernBERT-base 151M) (Hemant (heman10x))](https://modelscale.dev/models/jevbench-openjev-verdict) - [openJev Verdict 1.4 (Hemant (heman10x))](https://modelscale.dev/models/jevbench-openjev-verdict-1-4) - [openJev Verdict 1.4 (Hemant (heman10x))](https://modelscale.dev/models/openjev-verdict-1-4) - [openjev-sglang (Qwen3.6-35B-A3B on SGLang) (ekzhang)](https://modelscale.dev/models/jevbench-openjev-sglang) - [openjev-sglang Qwen3.6-35B-A3B (ekzhang)](https://modelscale.dev/models/openjev-sglang) - [OpenSourceJev (Qwen3.5-4B Q4_K_M, native llama.cpp) (sabeel111)](https://modelscale.dev/models/jevbench-opensourcejev-qwen35-4b-q4km) - [OpenSourceJev Qwen3.5-4B Q4_K_M (sabeel111)](https://modelscale.dev/models/opensourcejev-qwen35-4b-q4km) - [openvons (Not listed)](https://modelscale.dev/models/decision-index-0-3-openvons) - [Oracle NLI (BERT base ) binary subset (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-oracle-nli-bert-base-binary-subset) - [Oracle NLI (BERT large ) binary subset (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-oracle-nli-bert-large-binary-subset) - [OrcaCyber-Nano-1.0 (OrcaRouter)](https://modelscale.dev/models/orcacyber-nano-1-0) - [OriOn-Mistral-24B (LightOn)](https://modelscale.dev/models/orion-mistral-24b) - [OriOn-Qwen-32B (LightOn)](https://modelscale.dev/models/orion-qwen-32b) - [Ornith-1.0-35B (DeepReinforce AI)](https://modelscale.dev/models/ornith-1-0-35b) - [Ornith-1.0-397B (DeepReinforce AI)](https://modelscale.dev/models/ornith-1-0-397b) - [Ornith-1.0-9B (DeepReinforce AI)](https://modelscale.dev/models/ornith-1-0-9b) - [Ornith-1.5-122B (Ornith AI)](https://modelscale.dev/models/ornith-1-5-122b) - [PandaGPT 7B (PandaGPT authors)](https://modelscale.dev/models/pandagpt-7b) - [PandaLM-7B-v1 (JudgeBench) (PandaLM authors)](https://modelscale.dev/models/native-judgebench-pandalm-7b-v1) - [Parakeet CTC 1.1B (NVIDIA)](https://modelscale.dev/models/parakeet-ctc-1-1b) - [Parakeet Redux (Moondream)](https://modelscale.dev/models/parakeet-redux) - [Parakeet TDT 0.6B v3 (NVIDIA)](https://modelscale.dev/models/parakeet-tdt-0-6b-v3) - [Pareto 26.10 Preview (Unbiased)](https://modelscale.dev/models/pareto-26-10-preview) - [Pareto 26.9 (Unbiased)](https://modelscale.dev/models/pareto-26-9) - [Particle-1 (Particle AI)](https://modelscale.dev/models/particle-1) - [Perplexity Decider Flash v1.2 4B (Perplexity)](https://modelscale.dev/models/pplx-decider-flash-v1-2) - [Perplexity Decider Flash v1.3 4B (Perplexity)](https://modelscale.dev/models/pplx-decider-flash-v1-3) - [Perplexity Decider v1 27B (Perplexity)](https://modelscale.dev/models/pplx-decider-v1-27b) - [Perplexity Decider v1.1 (27B) (Perplexity)](https://modelscale.dev/models/decision-index-0-3-perplexity-decider-v1-1-27b) - [Perplexity Decider v1.2 27B (Perplexity)](https://modelscale.dev/models/pplx-decider-v1-2) - [Perplexity Decider v1.3 27B (Perplexity)](https://modelscale.dev/models/pplx-decider-v1-3) - [Pharia-1-LLM-7B-control (Aleph Alpha)](https://modelscale.dev/models/pharia-1-llm-7b-control) - [Pharia-1-LLM-7B-control-aligned (Aleph Alpha)](https://modelscale.dev/models/pharia-1-llm-7b-control-aligned) - [Phi-3.5-mini (Microsoft)](https://modelscale.dev/models/phi-3-5-mini) - [Phi-4 Multimodal Instruct (Microsoft)](https://modelscale.dev/models/phi-4-multimodal-instruct) - [Phi-4-reasoning (Microsoft)](https://modelscale.dev/models/phi-4-reasoning) - [Phi-4-reasoning-plus (Microsoft)](https://modelscale.dev/models/phi-4-reasoning-plus) - [Phonic-1 (Phonic)](https://modelscale.dev/models/phonic-1) - [Phonon-1 (Fermion Research)](https://modelscale.dev/models/phonon-1) - [Phonon-2 (Fermion Research)](https://modelscale.dev/models/phonon-2) - [Plumb-4B (crh225)](https://modelscale.dev/models/plumb-4b) - [Plumb-4B (crh225, JevK5 v0.2 + LoRA) (crh225)](https://modelscale.dev/models/jevbench-plumb-4b) - [Pokee-Isaac 28B (Pokee AI)](https://modelscale.dev/models/pokee-isaac-28b) - [pplx-embed-v2-late-0.6b (Perplexity)](https://modelscale.dev/models/pplx-embed-v2-late-0-6b) - [pplx-embed-v2-late-9b (Perplexity)](https://modelscale.dev/models/pplx-embed-v2-late-9b) - [Prometheus2-7b (JudgeBench) (Prometheus authors)](https://modelscale.dev/models/native-judgebench-prometheus2-7b) - [Prometheus2-8x7b (JudgeBench) (Prometheus authors)](https://modelscale.dev/models/native-judgebench-prometheus2-8x7b) - [Prometheus2-bgb-8x7b (JudgeBench) (Prometheus authors)](https://modelscale.dev/models/native-judgebench-prometheus2-bgb-8x7b) - [Prompt (gpt-3.5-turbo) (RAGTruth detector) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-prompt-gpt-3-5-turbo-detector) - [Prompt (gpt-4-turbo) (RAGTruth detector) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-prompt-gpt-4-turbo-detector) - [Quyet-1.0-Large (chinhnc)](https://modelscale.dev/models/decision-index-0-3-quyet-1-0-large) - [Qwen-2.5-1B-RLCD (harshatheg)](https://modelscale.dev/models/decision-index-0-3-qwen-2-5-1b-rlcd) - [Qwen-2.5-Nemotron-32B-Reward (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-qwen-2-5-nemotron-32b-reward) - [Qwen-3-Nemotron-32B-Reward (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-qwen-3-nemotron-32b-reward) - [Qwen-AgentWorld-35B-A3B (Alibaba)](https://modelscale.dev/models/qwen-agentworld-35b-a3b) - [Qwen-Audio 7B (Alibaba)](https://modelscale.dev/models/qwen-audio-7b) - [Qwen-Audio-Chat 7B (Alibaba)](https://modelscale.dev/models/qwen-audio-chat-7b) - [Qwen-VL-OCR (Alibaba)](https://modelscale.dev/models/qwen-vl-ocr) - [Qwen2-Audio 7B Instruct (Alibaba)](https://modelscale.dev/models/qwen2-audio-7b-instruct) - [Qwen2.5-Max (Alibaba)](https://modelscale.dev/models/qwen2-5-max) - [Qwen2.5-Omni 7B (Alibaba)](https://modelscale.dev/models/qwen2-5-omni-7b) - [Qwen3 235B-A22B (Alibaba)](https://modelscale.dev/models/qwen3-235b-a22b) - [Qwen3 235B-A22B (Reasoning) (Alibaba)](https://modelscale.dev/models/qwen3-235b-a22b-reasoning) - [Qwen3 32B (Alibaba)](https://modelscale.dev/models/qwen3-32b) - [Qwen3 32B (Reasoning) (Alibaba)](https://modelscale.dev/models/qwen3-32b-reasoning) - [Qwen3-ASR 0.6B (Alibaba)](https://modelscale.dev/models/qwen3-asr-0-6b) - [Qwen3-ASR 1.7B (Alibaba)](https://modelscale.dev/models/qwen3-asr-1-7b) - [Qwen3-Coder 480B-A35B (Alibaba)](https://modelscale.dev/models/qwen3-coder-480b-a35b) - [Qwen3-Nemotron-32B-GenRM-Principle (JudgeBench) (NVIDIA)](https://modelscale.dev/models/native-judgebench-qwen3-nemotron-32b-genrm-principle) - [Qwen3-Omni-30B-A3B-Thinking (Alibaba)](https://modelscale.dev/models/qwen3-omni-30b-a3b-thinking) - [Qwen3-Reranker-4B (Qwen)](https://modelscale.dev/models/jevbench-qwen3-reranker-4b) - [Qwen3-Reranker-4B (Alibaba)](https://modelscale.dev/models/qwen3-reranker-4b) - [Qwen3-VL-235B-A22B Instruct (Alibaba)](https://modelscale.dev/models/qwen3-vl-235b-a22b-instruct) - [Qwen3.5-0.8B Decision Model (Mourad Ghafiri)](https://modelscale.dev/models/mghafiri-qwen3-5-0-8b-decision-model) - [Qwen3.5-0.8B Decision Model (Mourad Ghafiri) (Mourad Ghafiri)](https://modelscale.dev/models/jevbench-mghafiri-qwen3-5-0-8b-decision-model) - [Qwen3.5-4B (Alibaba)](https://modelscale.dev/models/qwen3-5-4b) - [Qwen3.5-9B Jev-like data-mix v2 (jsaurabh)](https://modelscale.dev/models/jevbench-qwen35-9b-jev-data-mix-v2) - [Qwen3.5-9B Jev-like data-mix v2 (jsaurabh)](https://modelscale.dev/models/qwen35-9b-jev-data-mix-v2) - [Qwen3.8 27B (Chutes TEE) (Qwen / Chutes)](https://modelscale.dev/models/jevbench-qwen3-8-27b) - [Qwen3.8 Max Preview (Alibaba)](https://modelscale.dev/models/qwen3-8-max-preview) - [Qwen3.8-27B (Chutes TEE) (Alibaba)](https://modelscale.dev/models/qwen3-8-27b-chutes) - [Qwen4 27B (Alibaba)](https://modelscale.dev/models/qwen4-27b) - [Qwen4 Flash & Plus (Alibaba)](https://modelscale.dev/models/qwen4-flash-plus) - [QwQ-32B (Alibaba)](https://modelscale.dev/models/qwq-32b) - [R-LPS (FinancialPhraseBank) (Malo et al.)](https://modelscale.dev/models/native-financialphrasebank-r-lps) - [Raw Phi-4 mini direct logits (Microsoft / neutral reproduction)](https://modelscale.dev/models/jevbench-raw-phi-4-mini) - [Raw Phi-4 mini direct logits (Microsoft)](https://modelscale.dev/models/raw-phi-4-mini) - [Raw Qwen3 0.6B direct logits (Alibaba Qwen / neutral reproduction)](https://modelscale.dev/models/jevbench-raw-qwen3-0-6b) - [Raw Qwen3 0.6B direct logits (Alibaba)](https://modelscale.dev/models/raw-qwen3-0-6b) - [Raw Qwen3 1.7B direct logits (Alibaba Qwen / neutral reproduction)](https://modelscale.dev/models/jevbench-raw-qwen3-1-7b) - [Raw Qwen3 1.7B direct logits (Alibaba)](https://modelscale.dev/models/raw-qwen3-1-7b) - [Raw Qwen3 4B Instruct 2507 direct logits (Alibaba Qwen / neutral reproduction)](https://modelscale.dev/models/jevbench-raw-qwen3-4b-instruct-2507) - [Raw Qwen3 4B Instruct 2507 direct logits (Alibaba)](https://modelscale.dev/models/raw-qwen3-4b-instruct-2507) - [Raw Qwen3 8B direct logits (Alibaba Qwen / neutral reproduction)](https://modelscale.dev/models/jevbench-raw-qwen3-8b) - [Raw Qwen3 8B direct logits (Alibaba)](https://modelscale.dev/models/raw-qwen3-8b) - [razorback16 openjev diffusiongemma (NVFP4, vLLM) (Not listed)](https://modelscale.dev/models/decision-index-0-3-razorback16-openjev-diffusiongemma-nvfp4-vllm) - [reflex 4B (kshetrajna12)](https://modelscale.dev/models/reflex-4b) - [reflex 4B (kshetrajna12) (kshetrajna12)](https://modelscale.dev/models/jevbench-reflex-4b) - [reflex-27b (kshetrajna12)](https://modelscale.dev/models/reflex-27b) - [reflex-27b (Qwen3.8-27B) (kshetrajna12)](https://modelscale.dev/models/jevbench-reflex-27b) - [Rerank 5 Fast (Cohere)](https://modelscale.dev/models/cohere-rerank-5-fast) - [Rerank 5 Pro (Cohere)](https://modelscale.dev/models/cohere-rerank-5-pro) - [Ripple-65B Preview (Ricursive Intelligence)](https://modelscale.dev/models/ripple-65b-preview) - [RSI-Jev v5.0 VL 3B (shgao)](https://modelscale.dev/models/decision-index-0-3-rsi-jev-v5-0-vl-3b) - [Ryotide Qwen v0.3.1 (Not listed)](https://modelscale.dev/models/decision-index-0-3-ryotide-qwen-v0-3-1) - [Sage-A1.5-F16-GGUF (InternScience)](https://modelscale.dev/models/sage-a1-5-f16-gguf) - [Sage-A1.5-FP8 (InternScience)](https://modelscale.dev/models/sage-a1-5-fp8) - [Sage-A1.5-Q4_K_M-GGUF (InternScience)](https://modelscale.dev/models/sage-a1-5-q4-k-m-gguf) - [Sage-A1.5-Q8_0-GGUF (InternScience)](https://modelscale.dev/models/sage-a1-5-q8-0-gguf) - [Sakana Fugu (Sakana AI)](https://modelscale.dev/models/sakana-fugu) - [Sakana Fugu-Ultra (Sakana AI)](https://modelscale.dev/models/sakana-fugu-ultra) - [Sakana Fugu-Ultra v1.1 (Sakana AI)](https://modelscale.dev/models/sakana-fugu-ultra-v1-1) - [Sakana Namazu (Sakana AI)](https://modelscale.dev/models/sakana-namazu) - [SALMONN 13B (SALMONN authors)](https://modelscale.dev/models/salmonn-13b) - [SALMONN 7B (SALMONN authors)](https://modelscale.dev/models/salmonn-7b) - [ScaleDown Classify (ScaleDown)](https://modelscale.dev/models/scaledown-classify) - [ScaleDown Compress (ScaleDown)](https://modelscale.dev/models/scaledown-compress) - [ScaleDown Extract (ScaleDown)](https://modelscale.dev/models/scaledown-extract) - [ScaleDown Summarize (ScaleDown)](https://modelscale.dev/models/scaledown-summarize) - [Scribe v2.2 Realtime (ElevenLabs)](https://modelscale.dev/models/scribe-v2-2-realtime) - [Scribe v3 (ElevenLabs)](https://modelscale.dev/models/scribe-v3) - [Scribe v3 Live (ElevenLabs)](https://modelscale.dev/models/scribe-v3-live) - [Seed 2.1 Pro (ByteDance)](https://modelscale.dev/models/seed-2-1-pro) - [Seed 2.1 Turbo (ByteDance)](https://modelscale.dev/models/seed-2-1-turbo) - [SeedRealtime (ByteDance)](https://modelscale.dev/models/seedrealtime) - [SelfCheckGPT (gpt-3.5-turbo) (RAGTruth detector) (RAGTruth authors)](https://modelscale.dev/models/native-ragtruth-selfcheckgpt-gpt-3-5-turbo-detector) - [SemIf (Not listed)](https://modelscale.dev/models/decision-index-0-3-semif) - [SemIf Qwen3.5-4B (Theodore Lee (TheoLeeCJ))](https://modelscale.dev/models/semif-qwen3-5-4b) - [SemIf, formerly OpenJev (Qwen3.5-4B, TheoLeeCJ) (Theodore Lee (TheoLeeCJ))](https://modelscale.dev/models/jevbench-semif-qwen3-5-4b) - [Sieve 2B (sthanika-ai)](https://modelscale.dev/models/decision-index-0-3-sieve-2b) - [Sieve 9B (sthanika-ai)](https://modelscale.dev/models/decision-index-0-3-sieve-9b) - [Sifr 0.8B v3.1 (Not listed)](https://modelscale.dev/models/decision-index-0-3-sifr-0-8b-v3-1) - [simple-jev · Qwen3.8-27B (Featherless AI)](https://modelscale.dev/models/decision-index-simple-jev-qwen3-8-27b) - [SimpleJev (Qwen3.5-0.8B, CPU) (sabeel111 / Featherless AI)](https://modelscale.dev/models/jevbench-simplejev-qwen3-5-0-8b) - [SimpleJev Qwen3.5-0.8B (Featherless AI)](https://modelscale.dev/models/simplejev-qwen3-5-0-8b) - [SimpleJev Qwen3.6-35B-A3B (Featherless AI)](https://modelscale.dev/models/jevbench-simplejev-qwen3-6-35b-a3b) - [SimpleJev Qwen3.6-35B-A3B (Featherless AI)](https://modelscale.dev/models/simplejev-qwen3-6-35b-a3b) - [SimpleJev Qwen3.8-27B (Featherless AI)](https://modelscale.dev/models/jevbench-simplejev-qwen3-8-27b) - [SimpleJev Qwen3.8-27B (Featherless AI)](https://modelscale.dev/models/simplejev-qwen3-8-27b) - [Skywork-Critic-Llama-3.1-70B (JudgeBench) (Skywork)](https://modelscale.dev/models/native-judgebench-skywork-critic-llama-3-1-70b) - [Skywork-Critic-Llama-3.1-8B (JudgeBench) (Skywork)](https://modelscale.dev/models/native-judgebench-skywork-critic-llama-3-1-8b) - [Skywork-Reward-Gemma-2-27B (JudgeBench) (Skywork)](https://modelscale.dev/models/native-judgebench-skywork-reward-gemma-2-27b) - [Skywork-Reward-Llama-3.1-8B (JudgeBench) (Skywork)](https://modelscale.dev/models/native-judgebench-skywork-reward-llama-3-1-8b) - [SLAM-Omni (X-LANCE)](https://modelscale.dev/models/slam-omni) - [smalljev semantic-v9 (Aditya (isHeSatoshi))](https://modelscale.dev/models/jevbench-smalljev) - [smalljev semantic-v9 (Aditya (isHeSatoshi))](https://modelscale.dev/models/smalljev) - [Solar Open 2 (Upstage)](https://modelscale.dev/models/solar-open-2) - [Solar Pro 2 (Upstage)](https://modelscale.dev/models/solar-pro-2) - [Solar Pro 4 (Upstage)](https://modelscale.dev/models/solar-pro-4) - [Solomon v1.1 (Not listed)](https://modelscale.dev/models/decision-index-0-3-solomon-v1-1) - [Soofi S 30B-A3B (Soofi Project)](https://modelscale.dev/models/soofi-s-30b-a3b) - [SOV-Transcribe-1 (Salesforce)](https://modelscale.dev/models/sov-transcribe-1) - [Span NLI (BERT base ) binary subset (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-span-nli-bert-base-binary-subset) - [Span NLI (BERT large ) binary subset (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-span-nli-bert-large-binary-subset) - [Span TF-IDF+Cosine (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-span-tf-idf-cosine) - [Span TF-IDF+SVM (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-span-tf-idf-svm) - [spark-s1-4b-v6 (Abhishek Rai (abhishek085))](https://modelscale.dev/models/spark-s1-4b-v6) - [spark-s1-4b-v6 (Open Spark Jev, abhishek085) (Abhishek Rai (abhishek085))](https://modelscale.dev/models/jevbench-spark-s1-4b-v6) - [SpeechGPT 7B (OpenMOSS)](https://modelscale.dev/models/speechgpt-7b) - [SQuAD (BERT base ) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-squad-bert-base) - [SQuAD (BERT large ) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-squad-bert-large) - [Standard One 8B (Standard Thinking)](https://modelscale.dev/models/standardone-8b) - [Standard One 8B (Standard Thinking) (Standard Thinking (myeongho12))](https://modelscale.dev/models/jevbench-standardone-8b) - [Step-Audio (StepFun)](https://modelscale.dev/models/step-audio) - [Step-Audio-Chat 130B (StepFun)](https://modelscale.dev/models/step-audio-chat-130b) - [SubQ Snap 1.1 (Subquadratic)](https://modelscale.dev/models/subq-snap-1-1) - [Surogate Rune 26B-A4B v3 (Surogate)](https://modelscale.dev/models/decision-index-rune-26b-a4b-v3) - [Surogate Rune 26B-A4B v3 (RTX PRO 6000) (unknown)](https://modelscale.dev/models/jevbench-surogate-rune-26b-a4b-v3-rtxpro6000-a2) - [Surogate Rune 26B-A4B v3 (RTX PRO 6000) (Surogate)](https://modelscale.dev/models/surogate-rune-26b-a4b-v3-rtxpro6000-a2) - [SVM-MPQA (FinancialPhraseBank) (Malo et al.)](https://modelscale.dev/models/native-financialphrasebank-svm-mpqa) - [swanOne (blockbrain)](https://modelscale.dev/models/swanone) - [swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) (blockbrain)](https://modelscale.dev/models/jevbench-swanone) - [SWE-1.7 (Cognition)](https://modelscale.dev/models/swe-1-7) - [SWE-2 (Cognition)](https://modelscale.dev/models/swe-2) - [SWE-2 Flash (Cognition)](https://modelscale.dev/models/swe-2-flash) - [Symbol (BERT base ) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-symbol-bert-base) - [Symbol (BERT large ) (ContractNLI) (Koreeda and Manning)](https://modelscale.dev/models/native-contractnli-symbol-bert-large) - [system-one (Qwen3-8B, Sean Goedecke) (Sean Goedecke)](https://modelscale.dev/models/jevbench-system-one-sg) - [system-one Qwen3-8B (Sean Goedecke)](https://modelscale.dev/models/system-one-sg) - [system-one-gemma (Not listed)](https://modelscale.dev/models/decision-index-0-3-system-one-gemma) - [system-one-open (mithalouni)](https://modelscale.dev/models/system-one-open) - [system-one-open (Gemma 4 E2B LoRA on an L4) (mithalouni)](https://modelscale.dev/models/jevbench-system-one-open) - [Table-BERT (GNN-TabFact comparison) (TabFact authors)](https://modelscale.dev/models/native-tabfact-table-bert-maintainer) - [Table-BERT-Horizontal-F+T-Concatenate (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-table-bert-horizontal-f-t-concatenate) - [Table-BERT-Horizontal-F+T-Template (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-table-bert-horizontal-f-t-template) - [Table-BERT-Horizontal-T+F-Template (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-table-bert-horizontal-t-f-template) - [Table-BERT-Vertical-F+T-Template (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-table-bert-vertical-f-t-template) - [Table-BERT-Vertical-T+F-Template (TabFact) (TabFact authors)](https://modelscale.dev/models/native-tabfact-table-bert-vertical-t-f-template) - [Ternary Bonsai 1.7B (Prism ML)](https://modelscale.dev/models/ternary-bonsai-1-7b) - [Ternary Bonsai 27B (Prism ML)](https://modelscale.dev/models/ternary-bonsai-27b) - [Ternary Bonsai 4B (Prism ML)](https://modelscale.dev/models/ternary-bonsai-4b) - [Ternary Bonsai 8B (Prism ML)](https://modelscale.dev/models/ternary-bonsai-8b) - [Tev1-0.8B-experimental (togethercomputer)](https://modelscale.dev/models/decision-index-0-3-tev1-0-8b-experimental) - [Tev1-4B-experimental (togethercomputer)](https://modelscale.dev/models/decision-index-0-3-tev1-4b-experimental) - [this-that 1.2 (Not listed)](https://modelscale.dev/models/decision-index-0-3-this-that-1-2) - [Thunder-LLM 8B (Academic)](https://modelscale.dev/models/thunder-llm) - [Toast 1 (Mixedbread)](https://modelscale.dev/models/toast-1) - [Torchcast Decision 27B (Not listed)](https://modelscale.dev/models/decision-index-0-3-torchcast-decision-27b) - [typecastlm (Mikhail Gribov)](https://modelscale.dev/models/typecastlm) - [typecastlm (Mikhail Gribov, Qwen3.5-4B computed head) (Mikhail Gribov)](https://modelscale.dev/models/jevbench-typecastlm) - [UI-Mate-27B (Tencent)](https://modelscale.dev/models/ui-mate-27b) - [UI-Mate-9B (Tencent)](https://modelscale.dev/models/ui-mate-9b) - [Ultramarine 1 Flash (Paper Instruments)](https://modelscale.dev/models/ultramarine-1-flash) - [Ultravox GLM-4P6 (Fixie AI)](https://modelscale.dev/models/ultravox-glm-4p6) - [Ultravox GLM-4P7 (Fixie AI)](https://modelscale.dev/models/ultravox-glm-4p7) - [Ultravox v0.4.1 Llama 3.1 8B (Fixie AI)](https://modelscale.dev/models/ultravox-v0-4-1-llama-3-1-8b) - [Ultravox v0.5 Llama 3.1 8B (Fixie AI)](https://modelscale.dev/models/ultravox-v0-5-llama-3-1-8b) - [Ultravox v0.5 Llama 3.2 1B (Fixie AI)](https://modelscale.dev/models/ultravox-v0-5-llama-3-2-1b) - [Ultravox v0.6 Llama 3.3 70B (Fixie AI)](https://modelscale.dev/models/ultravox-v0-6-llama-3-3-70b) - [Ultravox v0.7 (Fixie AI)](https://modelscale.dev/models/ultravox-v0-7) - [Vanilla (gpt-4o-2024-05-13) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-vanilla-gpt-4o-2024-05-13) - [Vanilla (Mistral-7B-v0.1-Instruct) (JudgeBench) (JudgeBench evaluated system)](https://modelscale.dev/models/native-judgebench-vanilla-mistral-7b-v0-1-instruct) - [Varco (NC AI)](https://modelscale.dev/models/varco) - [Verdict (Not listed)](https://modelscale.dev/models/decision-index-0-3-verdict) - [verdict-small (Manavarya09 (Manav))](https://modelscale.dev/models/verdict-small) - [verdict-small (Manavarya09, multilingual-e5-small 118M) (Manavarya09 (Manav))](https://modelscale.dev/models/jevbench-verdict-small) - [VertexAI Evaluation (gemini-1.5-pro-001) (JudgeBench) (JudgeBench authors)](https://modelscale.dev/models/native-judgebench-vertexai-evaluation-gemini-1-5-pro-001) - [VibeVoice-ASR-Streaming 1.5B (Microsoft)](https://modelscale.dev/models/vibevoice-asr-streaming-1-5b) - [VibeVoice-ASR-Streaming 7B (Microsoft)](https://modelscale.dev/models/vibevoice-asr-streaming-7b) - [VITA 1.0 (VITA-MLLM)](https://modelscale.dev/models/vita-1-0) - [VITA 1.5 (VITA-MLLM)](https://modelscale.dev/models/vita-1-5) - [vLLM-SR Decision 2.0 Eos 0.8B (Not listed)](https://modelscale.dev/models/decision-index-0-3-vllm-sr-decision-2-0-eos-0-8b) - [vLLM-SR Decision 2.0 Kai 0.6B (Not listed)](https://modelscale.dev/models/decision-index-0-3-vllm-sr-decision-2-0-kai-0-6b) - [vLLM-SR Decision 2.0 Lux 9B (Not listed)](https://modelscale.dev/models/decision-index-0-3-vllm-sr-decision-2-0-lux-9b) - [vLLM-SR Decision 2.0 Nox 4B (Not listed)](https://modelscale.dev/models/decision-index-0-3-vllm-sr-decision-2-0-nox-4b) - [vLLM-SR Decision 2.0 Sol 2B (Not listed)](https://modelscale.dev/models/decision-index-0-3-vllm-sr-decision-2-0-sol-2b) - [vLLM-SR Decision 2.0 Vega 27B (Not listed)](https://modelscale.dev/models/decision-index-0-3-vllm-sr-decision-2-0-vega-27b) - [Von (wfzyx, Option-Marker 395M) (wfzyx (Victor Hugo))](https://modelscale.dev/models/jevbench-von-395m) - [Von 1.3 (Not listed)](https://modelscale.dev/models/decision-index-0-3-von-1-3) - [Von 395M (wfzyx (Victor Hugo))](https://modelscale.dev/models/von-395m) - [Voxtral 4B TTS 2603 (Mistral AI)](https://modelscale.dev/models/voxtral-4b-tts-2603) - [Voxtral Mini 4B Realtime 2602 (Mistral AI)](https://modelscale.dev/models/voxtral-mini-4b-realtime-2602) - [Voxtral Mini Transcribe 3 (Mistral AI)](https://modelscale.dev/models/voxtral-mini-transcribe-3) - [Voxtral Mini Transcribe Realtime 3 (Mistral AI)](https://modelscale.dev/models/voxtral-mini-transcribe-realtime-3) - [Voxtral Small Transcribe 3 (Mistral AI)](https://modelscale.dev/models/voxtral-small-transcribe-3) - [Voxtral TTS 3 (Mistral AI)](https://modelscale.dev/models/voxtral-tts-3) - [W-Loughran (FinancialPhraseBank) (Malo et al.)](https://modelscale.dev/models/native-financialphrasebank-w-loughran) - [W-MPQA (FinancialPhraseBank) (Malo et al.)](https://modelscale.dev/models/native-financialphrasebank-w-mpqa) - [Whisper large-v3-turbo (OpenAI)](https://modelscale.dev/models/whisper-large-v3-turbo) - [Winnow-12B Q8 (Eldan Ring)](https://modelscale.dev/models/jevbench-winnow-12b) - [Winnow-12B Q8 (Eldan Ring)](https://modelscale.dev/models/winnow-12b) - [Winnow-E4B (EldanRing)](https://modelscale.dev/models/decision-index-0-3-winnow-e4b) - [Wispr Canto (Wispr)](https://modelscale.dev/models/wispr-canto) - [XLM-R large (550M) (Belebele English fine-tuning) (Belebele authors)](https://modelscale.dev/models/native-belebele-xlm-r-large-550m-english-fine-tuning) - [XLM-R large (550M) (Belebele Translate-Train-All) (Belebele authors)](https://modelscale.dev/models/native-belebele-xlm-r-large-550m-translate-train-all) - [XLM-V large (1.2B) (Belebele English fine-tuning) (Belebele authors)](https://modelscale.dev/models/native-belebele-xlm-v-large-1-2b-english-fine-tuning) - [XLM-V large (1.2B) (Belebele Translate-Train-All) (Belebele authors)](https://modelscale.dev/models/native-belebele-xlm-v-large-1-2b-translate-train-all) - [Xor 1.2 (Not listed)](https://modelscale.dev/models/decision-index-0-3-xor-1-2) - [Xor 26B-A4B (juspay)](https://modelscale.dev/models/decision-index-0-3-xor-26b-a4b) - [ZAYA1-74B-Preview (Zyphra)](https://modelscale.dev/models/zaya1-74b-preview) - [ZAYA1-VL-8B (Zyphra)](https://modelscale.dev/models/zaya1-vl-8b) - [ZeroEntropy zerank-2 (ZeroEntropy)](https://modelscale.dev/models/jevbench-zerank-2) - [ZeroEntropy zerank-2 (ZeroEntropy)](https://modelscale.dev/models/zerank-2) - [Zev (Not listed)](https://modelscale.dev/models/decision-index-0-3-zev) - [Zonos 2 (Zyphra)](https://modelscale.dev/models/zonos-2) ## Optional - [llms-full.txt](https://modelscale.dev/llms-full.txt): The expansive companion to this file: every model with its capability, price and runtime figures, every benchmark leaderboard, every article, and the markdown URL for each. - [Sitemap index](https://modelscale.dev/sitemap.xml): A sitemap index over five child sitemaps — pages, models, leaderboards, comparisons, articles — each dated by the source's own generation time. - [Articles feed (RSS)](https://modelscale.dev/feeds/articles.xml): RSS 2.0 for /articles. - [Articles feed (JSON Feed)](https://modelscale.dev/feeds/articles.json): JSON Feed 1.1 for /articles. - [robots.txt](https://modelscale.dev/robots.txt): Crawl rules. Everything is allowed except /api, which serves this site's own JSON. Every model profile and every leaderboard also has a markdown representation at the page's own path with `/md` in front of it — https://modelscale.dev/md/models/claude-fable-5-1 for https://modelscale.dev/models/claude-fable-5-1. They carry the same figures with the same rounding and the same evidence dates as the pages, as `text/markdown`.