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.
Meta · Open Weight · rank 70 · bench-align-v5
Muse Spark Open is built for reasoning. It ranks in the top quarter for multimodal tasks (top 17% of 136 scored models) and reasoning (top 21% of 216 scored models), by BenchLM's published scores. It accepts text, images, files, audio and video and produces text.
Muse Spark Open by Meta scores 55.8 overall, costs $1.25 per 1M input tokens and $4.25 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.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
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 | 9.75 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 183 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
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.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 24.9 | #84 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 89.0 | #51 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 43.9 | #30 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 25.8 | #29 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 42.0 | #51 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 28.0 | #194 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| SWE-Atlas Codebase QnA SWE-Atlas Codebase QnA | 58.0 | #4 | 124 codebase questions across 11 repositories | Production codebase comprehension | Muse Spark 1.3 Evaluation Methodology |
| AA-SciCode Artificial Analysis SciCode | 58.4 | #17 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| DeepSWE DeepSWE | 60.0 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 78.3 | #67 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| CritPt Critical Physics Tasks | 14.9 | #53 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA Briefcase Artificial Analysis Briefcase | 1279 | #41 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 49.7 | #37 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| HLE w/ tools Humanity's Last Exam with tools | 61.0 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 80.9 | #17 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1303 | #15 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| ZeroBench ZeroBench | 50.0 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| NYT Connections NYT Connections LLM Benchmark (extended version) | 78.4 | #42 | 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) | 44.1 | #24 | 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) |
| #47 |
| 113 software engineering tasks across 91 repositories and 5 languages |
| Long-horizon software engineering |
| DeepSWE benchmark blog |
| FrontierCode 2.0 FrontierCode 2.0 | 6.5 | #32 | 132 private software-engineering tasks | Frontier coding-agent quality | FrontierCode 2.0 |
| #8 |
| Expert questions with tool use |
| Frontier tool-augmented reasoning |
| DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA | 1401 | #48 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 45.1 | #40 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 8.1 | #41 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 18.6 | #34 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| JobBench JobBench | 61.8 | #8 | 130 tasks across 35 occupations | Professional multi-source workflows | JobBench: Aligning Agent Work With Human Will |
| MCP Atlas MCP Atlas | 89.2 | #1 | Tool-integrated agent tasks | Advanced tool use | Introducing GPT-5.4 mini and nano |
| Toolathlon-Verified Toolathlon-Verified | 72.8 | #16 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 0 | #28 | 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 |
| #1 |
| 100 visual reasoning questions |
| Tool-augmented visual reasoning |
| Muse Spark Eval Methodology |
| SimpleVQA SimpleVQA | 73.6 | #4 | Visual QA tasks | General visual understanding | GLM-5V-Turbo |
| BabyVision BabyVision | 80.2 | #2 | Visual perception tasks | Fine-grained visual perception | Muse Spark 1.1 Evaluation Report |
| 85.6 |
| #1 |
| 20 private honeypot tasks across 7 domains with exploitable evaluators |
| Agentic alignment and specification gaming |
| HoneyBench v0.2 |