Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Anthropic · Proprietary · rank 13 · bench-align-v5
Claude Sonnet 5.5 is built for coding, agent work and reasoning. It ranks in the top quarter for coding (top 2% of 210 scored models) and knowledge (top 8% of 283 scored models), by BenchLM's published scores.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
Claude Sonnet 5.5 by Anthropic scores 77.9 overall, costs $2.00 per 1M input tokens and $10.00 per 1M output tokens, and carries a context window of 1M tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 286.89 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 147 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| $5.00 |
| Batch cache read / 1M tokens (OpenRouter batch) | $0.05 |
| Batch cache write / 1M tokens (OpenRouter batch) | $1.25 |
Batch API rate (asynchronous jobs), from OpenRouter's batch listing.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Plans from the model's maker, and the API providers that list this exact model today. Links leave ModelScale; each provider sets its own prices and limits.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| HealthBench (raw) HealthBench raw score | 69.4 | #1 | 5,000 multi-turn patient conversations | Realistic healthcare conversations | HealthBench: Evaluating Large Language Models Towards Improved Human Health |
| HealthBench (length-adjusted) HealthBench length-adjusted score | 65.4 | #1 | 5,000 multi-turn patient conversations | Realistic healthcare conversations | HealthBench: Evaluating Large Language Models Towards Improved Human Health |
| HealthBench Professional (raw) HealthBench Professional raw score | 77.1 | #1 | 525 physician-authored conversations | Professional clinical tasks | HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats |
| BioMysteryBench (human-solvable) BioMysteryBench Human Solvable | 89.2 | #3 | Human-solvable computational biology investigations | Expert computational biology | Claude Opus 5 System Card |
| BioMysteryBench (human-difficult) BioMysteryBench Human Difficult | 44.7 | #4 | Human-difficult computational biology investigations | Frontier computational biology | Claude Opus 5 System Card |
| SpatialBench Verified LatchBio SpatialBench Verified | 72.5 | #1 | 115 externally validated spatial transcriptomics problems | Professional bioinformatics | Claude Opus 5 System Card |
| SingleCellBench LatchBio SingleCellBench | 59.1 | #5 | 195 single-cell RNA sequencing problems | Professional bioinformatics | Claude Opus 5 System Card |
| Protein Design Anthropic Protein Design evaluation | 51.0 | #3 | Constrained protein-sequence design tasks | Computational protein design | Claude Opus 5 System Card |
| Protocols (troubleshooting) Molecular Biology Protocols Troubleshooting | 67.3 | #4 | Molecular-biology protocol troubleshooting | Expert laboratory protocols | Claude Opus 5 System Card |
| Protocols (understanding) Benchling Molecular Biology Protocols Understanding | 66.6 | #3 | Molecular-biology protocol extension | Expert laboratory protocols | Claude Opus 5 System Card |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 54.5 | #11 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-HLE Artificial Analysis Humanity's Last Exam | 55.0 | #6 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 30.5 | #17 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 51.5 | #21 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 43.3 | #158 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HealthBench Professional HealthBench Professional | 69.2 | #1 | Clinician chat tasks | Professional clinical workflows | HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats |
| HLE w/o tools Humanity's Last Exam without tools | 56.9 | #5 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| Morphology-to-molecule matching Axiom Bio morphology-to-molecule matching | 25.0 | #4 | Four multi-channel cell-imaging perturbation-matching tasks | Biomedical image and molecular reasoning | Claude Opus 5.5 System Card |
| Medicinal chemistry Anthropic medicinal-chemistry evaluation | 65.3 | #2 | 504 molecular-property questions | Medicinal chemistry reasoning | Claude Opus 5.5 System Card |
| Protein Design library ranking Anthropic protein-design library-ranking task | 54.8 | #2 | 83 protein-design library-ranking problems | Computational protein design | Claude Opus 5.5 System Card |
| De novo protein-binder design Anthropic de novo protein-binder design evaluation | 82.3 | #3 | 15 protein targets | Long-horizon computational protein design | Claude Opus 5.5 System Card |
| HealthBench (raw, Artificial Analysis) Artificial Analysis HealthBench raw score | 65.9 | #1 | 5,000 conversations | Health conversation evaluation | HealthBench independent evaluation |
| HealthBench (length-adjusted, Artificial Analysis) Artificial Analysis HealthBench length-adjusted score | 62.1 | #1 | 5,000 conversations | Health conversation evaluation | HealthBench independent evaluation |
| HealthBench Professional (length-adjusted, Artificial Analysis) Artificial Analysis HealthBench Professional length-adjusted score | 63.0 | #3 | 525 conversations | Health conversation evaluation | HealthBench Professional independent evaluation |
| HealthBench Professional (raw, Artificial Analysis) Artificial Analysis HealthBench Professional raw score | 70.8 | #3 | 525 conversations | Health conversation evaluation | HealthBench Professional independent evaluation |
| PhysicianBench PhysicianBench | 63.2 | #3 | 100 EHR physician tasks | Clinical agent work | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| SWE-bench Pro SWE-bench Pro | 81.3 | #3 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| FrontierCode 1.1 Main FrontierCode 1.1 Main | 46.2 | #8 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | FrontierCode leaderboard |
| FrontierCode 1.1 Extended FrontierCode 1.1 Extended | 59.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 88.772 | #11 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 80.488 | #13 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
| ArXivMath Aug. 2026 (no tools) ArXivMath August 2026 without tools |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 82.7 | #23 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 41.7 | #7 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 31.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GMMLU Global MMLU | 92.1 | #5 | Knowledge questions across 42 languages | Multilingual knowledge | Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation |
| MILU Multi-task Indic Language Understanding Benchmark | 91.6 | #5 | Knowledge tasks across 11 languages | Multilingual Indic knowledge | MILU: A Multi-task Indic language understanding benchmark |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| DRACO Data Research and Analysis with Complex Operations | 87.0 | #5 | Agentic data research and analysis tasks | Professional data analysis | Claude Opus 5 System Card |
| LAB all-pass (Harvey held-out) Legal Agent Benchmark all-pass rate — Harvey held-out set | 10.0 | #2 | Harvey-held-out legal-agent tasks | Professional legal work | Claude Opus 5 System Card |
| LAB criterion-pass (Harvey held-out) Legal Agent Benchmark mean criterion-pass rate — Harvey held-out set |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chartography (no tools) Chartography without tools | 61.6 | #6 | 100 specialized chart types | Professional chart reasoning | Chartography |
| Chartography (tools) Chartography with image and code tools | 90.2 | #2 | 100 specialized chart types | Professional chart reasoning | Chartography |
| BenchCAD Vision2Code (no tools) BenchCAD Vision2Code voxel IoU without tools | 0.747 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MaxxBench MaxxBench (mutated DeepSWE tasks) | 66.9 | #4 | 89 mutated DeepSWE feature-implementation tasks, two attempts per model | Long-horizon software engineering under changed requirements | Why MaxxBench (unLAP research post) |
| SpireClimb SpireClimb (Slay the Spire 1 and 2) | 1.3 | #10 | 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model | Maximum game difficulty, long-horizon computer use | SpireClimb (Epoch AI) |
| Chess Puzzles Chess Puzzles (Epoch AI) | 59.0 |
A second, independent score source. Epoch’s own figures in Epoch’s units, one line per model version Epoch evaluated (effort setting as Epoch labels it). They are not part of this site’s capability scores or rank.
| Benchmark | Variant | Score | Epoch date | Evidence |
|---|---|---|---|---|
| GPQA Diamond Accuracy on graduate-level science multiple-choice questions (best score across scorers). Unit: fraction (0–1); higher is better. | max | 0.9558 ± 0.0137 | 2026-09-29 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | max | 0.8877 ± 0.0187 | 2026-09-29 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | max | 0.8049 ± 0.0627 | 2026-09-29 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | max | 0.465 ± 0.0158 | 2026-09-29 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
People's votes between two anonymous answers on arena.ai, one board per task. LMArena's own ratings and ranks, one line per model version it rates; not part of this site's capability scores or rank.
| Board | Variant | Rating | Votes | Rank | Published | Evidence |
|---|---|---|---|---|---|---|
| Vision Arena People's votes between two answers about the same image, style-controlled. | xHigh | 1,264 ± 9 | 5,388 | 43 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #6 |
| 150 private software-engineering tasks |
| Frontier coding-agent quality |
| FrontierCode leaderboard |
| SWE Multilingual SWE Multilingual | 90.3 | #3 | Multilingual software-engineering tasks | Professional software engineering | MiniMax M2.7: Early Echoes of Self-Evolution |
| SWE Multimodal SWE-bench Multimodal | 54.3 | #5 | Multimodal software engineering tasks | Frontier multimodal coding | SWE-bench Multimodal |
| ProgramBench ProgramBench: Can Language Models Rebuild Programs From Scratch? | 79.7 | #6 | 200 program reconstruction tasks | Full-repository software architecture | ProgramBench: Can Language Models Rebuild Programs From Scratch? |
| FrontierSWE v2 FrontierSWE v2 | 61.9 | #4 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 51.3 | #5 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | Bug Hunt Bench method, caveats, and definitions |
| AA-SciCode Artificial Analysis SciCode | 61.0 | #6 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| DeepSWE DeepSWE | 71.0 | #24 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| VulcanBench Frontier v4 VulcanBench Frontier v4 | 92.0 | #4 | 23 behavioural-reconstruction coding tasks | Professional multi-file software engineering | VulcanBench Frontier v4 leaderboard |
| FrontierCode 2.0 FrontierCode 2.0 | 42.2 | #8 | 132 private software-engineering tasks | Frontier coding-agent quality | FrontierCode 2.0 |
| 86.8 |
| #2 |
| 57 recent research-mathematics problems |
| Research mathematics |
| Claude Opus 5.5 System Card |
| ArXivMath Aug. 2026 (tools) ArXivMath August 2026 with tools | 95.2 | #2 | 57 recent research-mathematics problems | Research mathematics | Claude Opus 5.5 System Card |
| #7 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| 93.1 |
| #2 |
| Harvey-held-out legal-agent tasks |
| Professional legal work |
| Claude Opus 5 System Card |
| Toolathlon Verified Pass@3 Toolathlon Verified Pass@3 | 85.2 | #2 | 108 verified real-world tool-use tasks | Long-horizon application tool use | Claude Opus 5 System Card |
| Toolathlon Verified Pass³ Toolathlon Verified Pass cubed | 68.5 | #4 | 108 verified real-world tool-use tasks | Long-horizon application tool use | Claude Opus 5 System Card |
| Toolathlon Verified avg. turns Toolathlon Verified average assistant turns | 31.6 | #1 | 108 verified real-world tool-use tasks | Long-horizon application tool use | Claude Opus 5 System Card |
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 70.60 | #1 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| Terminal-Bench-Science 0.1 Terminal-Bench-Science 0.1 | 59.9 | #6 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | Terminal-Bench-Science 0.1 |
| AA Briefcase Artificial Analysis Briefcase | 1811 | #1 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 71.8 | #10 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA Harvey LAB v1.0 Artificial Analysis Harvey LAB-AA v1.0 | 93.1 | #5 | Legal agent tasks | Professional legal work | Artificial Analysis Harvey LAB-AA Benchmark Leaderboard |
| HLE w/ tools Humanity's Last Exam with tools | 64.5 | #4 | Expert questions with tool use | Frontier tool-augmented reasoning | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA | 1844 | #5 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 66.9 | #4 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 63.6 | #4 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 25.8 | #17 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 57.5 | #3 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| Toolathlon-Verified Toolathlon-Verified | 77.8 | #3 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 83.1 | #6 | Difficult terminal tasks | Frontier agentic | Vals AI Terminal-Bench 2.1, Vals AI run leaderboard |
| AutomationBench (Zapier 1.0.6) AutomationBench, Zapier private evaluation set release 1.0.6 | 44.70 | #1 | 600+ held-out workflows across 47 simulated applications and six business domains | Long-horizon automation | AutomationBench |
| Hermes Index Hermes Index: agentic capability and cost per task inside Hermes Agent | 53.1 | #4 | Four suites: Hermes Bench (150 tasks), TerminalBench 4 without its 4 GPU tasks, TerminalBench Science and SkillsBench | Frontier agentic | Hermes Index: an agentic model leaderboard |
| Hermes Bench Hermes Bench: 150 agent tasks graded on the files and state the agent leaves behind | 73.5 | #6 | 150 tasks across 25 categories | Frontier agentic | Hermes Bench (Hermes Index) |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 8 | #15 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | MazeBench Results |
| Binary Exploitation Benchmark Anthropic Binary Exploitation Benchmark (formerly OSS-Fuzz), control-flow hijacks | 48 | #4 | Open-source function entry points | Exploit development | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 63.90 | #4 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| OSWorld 2.1 OSWorld 2.1 (all 108 tasks) | 80.1 | #3 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) |
| OSWorld 2.1 Offline OSWorld 2.1 offline subset (82 tasks) | 83.9 | #3 | 82 offline computer-use workflows | Long-horizon professional workflows | OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) |
| MKA Multimodal Knowledge Agent Benchmark | 52.0 | #7 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| #1 |
| 1,000-file Vision2Code subset |
| Programmatic CAD generation |
| BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD |
| BenchCAD Vision2Code (tools) BenchCAD Vision2Code voxel IoU with tools | 0.963 | #1 | 1,000-file Vision2Code subset | Programmatic CAD generation | BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD |
| OfficeQA OfficeQA | 76.9 | #5 | Historical Treasury Bulletin questions | Professional document reasoning | Claude Opus 5 System Card |
| Design Arena Website Design Arena Website Elo | 1305 | #14 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| OfficeQA Pro OfficeQA Pro | 65.6 | #8 | Document and spreadsheet tasks | Enterprise grounded reasoning | OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning |
| Biomedical image analysis Anthropic biomedical-image-analysis evaluation | 72.2 | #3 | 91 cases across 31 biomedical imaging tasks | Biomedical image analysis | Claude Opus 5.5 System Card |
| ParseBench-1 ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release) | 69.21 | #14 | 2,078 human-verified enterprise pages from insurance, finance and government documents | No method is strong on all five dimensions; charts and visual grounding separate the field | ParseBench: A Document Parsing Benchmark for AI Agents |
| ExtractBench (LlamaIndex) ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard) | 94.68 | #2 | 370 documents, 4,869 pages, 8 business domains, 67 document types, each with a JSON Schema | Short documents are near solved; long record lists and grounding separate systems | ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction |
| ExtractBench Pro ExtractBench Pro: long-tail document extraction challenges (LlamaIndex) | 32 | #4 | 100 synthetic documents, 2,622 pages, 86 document types, six challenge groups | The best system completes 58 of 100 documents perfectly; several complete none | ExtractBench Pro leaderboard and challenge descriptions |
| ParseBench-2 ParseBench-2: severity-aware document parsing (LlamaIndex leaderboard) | 74.94 | #11 | 4,317 page-level test cases from 2,645 documents in 13 datasets | Charts and visual grounding separate the field; several systems that lead on text and tables score near zero on charts | ParseBench-2: Severity-Aware Evaluation of Document Parsing |
| #11 |
| 100 programmatically generated chess positions with a single best move |
| Novel chess positions, single best move |
| Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 65.0 | #8 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| Furniture Assembly Furniture Assembly Benchmark (Epoch AI) | 75.0 | #8 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | Furniture Assembly Benchmark (Epoch AI) |
| MirrorCode MirrorCode (Epoch AI and METR) | 97.8 | #1 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | MirrorCode (Epoch AI) |
| FACTS Multimodal FACTS Multimodal | 50.4 | #9 | About 1,500 image questions: 711 public and 811 held out | Image-grounded factual answering | BenchLM |
| DAYJOB DAYJOB | 21.7 | #2 | 130 long-horizon tasks: 80 finance and 50 healthcare | Long-horizon professional work | BenchLM |
| DAYJOB Healthcare DAYJOB Healthcare | 16.0 | #2 | 50 long-horizon healthcare tasks across five subfields | Long-horizon clinical and healthcare operations work | BenchLM |
| FailureSensorIQ FailureSensorIQ | 67.4 | #5 | Multiple-choice questions on sensors and failure modes for 10 industrial assets | Industrial maintenance and reliability knowledge | BenchLM |
| Chart Arena Chart Arena | 1455 | #12 | 13 chart briefs with small datasets, rated by human votes | Data visualisation | BenchLM |
| Joke Arena Joke Arena | 1536 | #5 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | BenchLM |
| Pelican Arena Pelican Arena | 1730 | #4 | One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes | Vector drawing and animation in code | BenchLM |
| ASCII Arena ASCII Arena | 1546 | #8 | ASCII drawings of subjects from Google's Quick, Draw! dataset, rated by human votes | Text-character drawing | BenchLM |
| Game Arena Go Game Arena Go | 1442 | #9 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | BenchLM |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 80.5 | #38 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 70.2 | #3 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | StealthMark: The AI Benchmark Explained (Stealth Models) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) | 41.6 | #19 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | HoneyBench v0.2 |