Reasoning
198-question Diamond subset; independent AA evaluation
- 01
- 02
- 03
- 03
- 03
- 25
Muse Spark
Across the task benchmarks we track, Muse Spark’s strongest relative results are in reasoning and knowledge work. On GPQA Diamond, it scores 88.4%, ranking #25 among 30 models with reported results in our dataset.
Updated: Data as of:
🥇
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| MCP-Atlas ↗April 2026 / public 500 | Tool use | 82.4%#1 of 5 |
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 40.7%#31 of 68 |
| IFBench ↗58 constraint types | Precise instruction following | 75.9%Joint #9 of 17 |
| GPQA ↗Diamond / Artificial Analysis | Reasoning | 88.38%#25 of 30 |
Model details
| Model | Muse Spark |
|---|---|
| Agent Index v1.2 | Insufficient coverage (1/7) · Preview |
| Creator | Meta (opens in a new tab) |
| Availability | Proprietary |
| Context size | 262,144 tokens |
| Max output | Not reported (opens in a new tab) |
| Knowledge cutoff | Not reported |
| License | Not reported |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
No provider pricing or performance reports have been added for this model yet.
Benchmark performance
Muse Spark in color, alongside leading models. Latest stored reports, best effort per report date.
GPQA Diamond ↗
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
- 33
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| AA-Briefcase1.1 / combined EloCombined Elo · Higher is better | 646 Elo | selection: best reported configuration per release · Muse Spark · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,006.05 Elo | Muse Spark; 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 88.384% | Muse Spark; 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamHLE — source does not specify subsetAccuracy · Higher is better | 58% | Contemplating mode; parallel agents. Tool access not explicit in cited prose. · subset: unspecified | Meta ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 42.8% | subset: full · No tools | Meta ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 50.4% | Later Meta evaluation report; keep separate from launch Contemplating-mode result. · subset: full · Tools enabled | Meta ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 40.7% | question count: 2158 · reported precision decimals: 1 · Muse Spark; original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/muse-spark · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| IFBench58 constraint typesAccuracy · Higher is better | 75.9% | selection: publisher default displayed configuration · Muse Spark | Artificial Analysis (opens in a new tab)independent |
| MCP-AtlasApril 2026 / public 500Task success · Higher is better | 82.4% | public 500; 100 tool calls | Scale AI ↗ (opens in a new tab)benchmark publisher |