Muse Spark: benchmark scores, price and ranking
Muse Spark from Meta AI ranks #32 of 741 LLMs on the LLMs Tiger aggregate benchmark score (53.8), based on 12 benchmark results captured up to 2026-10-05.
- Organisation
- Meta AI
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-04-08 (source: epoch)
- Aggregate rank
- #32 of 741 (score 53.8)
Relative to other models, Muse Spark is strongest on Epoch ECI (#5 of 205) and weakest on ProofBench (#25 of 43).
Muse Spark benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 152 | #5 of 205 | Epoch AI Benchmarking Hub | 2026-10-05 |
| Humanity's Last Exam | 40.6% | #1 of 29 | Epoch AI Benchmarking Hub | 2026-10-05 |
| MCP Atlas | 82.2% | #1 of 14 | Scale Labs MCP Atlas leaderboard | 2026-10-05 |
| LMArena Vision Elo | 1,294 | #2 of 22 | LMArena | 2026-10-05 |
| GPQA Diamond | 89.8% | #37 of 274 | Epoch AI Benchmarking Hub | 2026-10-05 |
| OTIS Mock AIME | 88.9% | #43 of 188 | Epoch AI Benchmarking Hub | 2026-10-05 |
| LMArena Text Elo | 1,489 | #7 of 28 | LMArena | 2026-10-05 |
| WebDev Arena | 1,513 | #16 of 63 | Epoch AI Benchmarking Hub | 2026-10-05 |
| SciCode | 51.5% | #28 of 100 | Epoch AI Benchmarking Hub | 2026-10-05 |
| CritPt | 11.3% | #35 of 111 | Epoch AI Benchmarking Hub | 2026-10-05 |
| LMArena Document Elo | 1,444 | #8 of 18 | LMArena | 2026-10-05 |
| ProofBench | 17.0% | #25 of 43 | Epoch AI Benchmarking Hub | 2026-10-05 |
Models ranked nearby
- #29 Gemini 3.7 Flash (high) (53.9)
- #30 Gemini 3 Pro Preview (53.9)
- #31 GLM-5.3 (max) (53.8)
- #33 Claude Opus 4.7 (max) (53.7)
- #34 GPT-6 Luna (max) (53.7)
- #35 DeepSeek R1 (0528) (53.6)
Compare it on the live leaderboard → · How the aggregate score works