Muse Spark
| Released | 2026-04-08 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 56.9 · rank 59 |
| Provider | Meta |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 56.9 | 59 | 14 |
| Overall: Coding | 53.7 | 80 | 5 |
| Overall: Reasoning | 57.8 | 58 | 8 |
| Overall: Agentic work | 56.4 | 68 | 4 |
| Overall: Frontend | 49.8 | 88 | 5 |
| Coding | 55.0 | 71 | 2 |
| Reasoning | 58.7 | 59 | 2 |
| Math | 55.8 | 62 | 4 |
| Knowledge | 59.5 | 28 | 2 |
| Frontend | 45.4 | 91 | 1 |
| General | 61.1 | 25 | 1 |
| Multimodal | 60.6 | 17 | 2 |
Evidence
Coding 55.0 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 74.4% | Vals AI | 2026-09-01 |
| SciCode | 51.5% | Epoch AI | 2026-11-11 |
Reasoning 58.7 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 11.3% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 89.8% | Epoch AI | 2026-04-08 |
| GPQA Diamond (Vals run) | 89.6% | Vals AI | 2026-09-01 |
Math 55.8 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 39.0% | Epoch AI | 2026-04-08 |
| ProofBench | 17.0% | Epoch AI | 2026-11-11 |
| FrontierMath Tier 4 (2025 set) | 14.6% | Epoch AI | 2026-04-08 |
| OTIS Mock AIME 2024-2025 | 88.9% | Epoch AI | 2026-04-08 |
Knowledge 59.5 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 40.6% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 87.3% | Vals AI | 2026-09-01 |
Frontend 45.4 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 19.7% | Vals AI | 2026-11-09 |
General 61.1 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,489 | LMArena | 2026-11-09 |
Multimodal 60.6 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 87.4% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,294 | LMArena | 2026-11-09 |
Names matched to this model
muse-spark