Muse Spark Open
| Released | 2026-10-15 |
|---|---|
| Price per 1M | $1.25 in · $4.25 out |
| Overall score | 58.0 · rank 54 |
| Context window | 1,048,576 tokens |
| Provider | Meta |
| Weights | Open weights (Muse Model License) |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.0 | 54 | 28 |
| Overall: Coding | 57.2 | 56 | 23 |
| Overall: Reasoning | 59.1 | 43 | 13 |
| Overall: Agentic work | 57.6 | 58 | 20 |
| Overall: Frontend | 54.2 | 64 | 6 |
| Coding | 58.4 | 42 | 3 |
| Agents | 57.0 | 60 | 9 |
| Reasoning | 58.8 | 57 | 8 |
| Math | 59.6 | 32 | 3 |
| Knowledge | 58.9 | 35 | 2 |
| Frontend | 52.1 | 65 | 3 |
| Value vs price | +8.1 | 45 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 53.4 ±3.1 | 8 |
| High | 59.0 ±5.8 | 3 |
| Low | 52.8 ±5.7 | 2 |
| Max | 51.9 ±6.7 | 1 |
| Medium | 56.3 ±5.7 | 2 |
| Extra High | 58.4 ±1.3 | 18 |
Evidence
Coding 58.4 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Coding | 55.1% | LiveBench | 2026-11-06 |
| Code Migration v1.1 | 26.9% | Vals AI | 2026-11-09 |
| SciCode | 58.5% | Epoch AI | 2026-11-11 |
Agents 57.0 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 6.6% | Vals AI | 2026-11-09 |
| APEX-Agents | 33.4% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 12.1% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 26.2% | LiveBench | 2026-11-06 |
| EMB v1.1 (Excel financial modeling) | 62.0% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 82.7% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 26.3% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 60.7% | Vals AI | 2026-11-09 |
| HLAB-Vals 1.1 (legal agent) | 25.0% | Vals AI | 2026-11-09 |
Reasoning 58.8 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 78.4% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 57.5% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 57.5% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 88.6% | Epoch AI | 2026-10-15 |
| CritPt | 14.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 89.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 89.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-3 | 0.1% | ARC Prize | 2026-11-11 |
| LiveBench 2.0 Reasoning | 73.7% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Data Analysis | 60.2% | LiveBench | 2026-11-06 |
Math 59.6 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 69.8% | Epoch AI | 2026-10-15 |
| FrontierMath Tier 4 | 31.7% | Epoch AI | 2026-10-15 |
| OTIS Mock AIME 2024-2025 | 98.1% | Epoch AI | 2026-10-15 |
Knowledge 58.9 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 56.6% | Epoch AI | 2026-10-15 |
| Legal Research Bench | 38.5% | Vals AI | 2026-11-09 |
Frontend 52.1 ±5.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 58.1% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 76.2% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,526 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 88.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 77.7% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 58.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 88.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 77.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 58.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 47.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 27.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 12.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 47.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 27.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 12.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.4% | ARC Prize | A stronger configuration result was used |
Names matched to this model
muse-spark-open, muse-spark-open-816b-a42b