Muse Spark 1.3
| Released | 2026-09-02 |
|---|---|
| Price per 1M | $1.25 in · $4.25 out |
| Overall score | 61.7 · rank 18 |
| Context window | 1,048,576 tokens |
| Provider | Meta |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 61.7 | 18 | 41 |
| Overall: Coding | 61.0 | 21 | 30 |
| Overall: Reasoning | 62.6 | 20 | 13 |
| Overall: Agentic work | 60.9 | 21 | 27 |
| Overall: Frontend | 60.5 | 18 | 13 |
| Coding | 61.3 | 16 | 9 |
| Agents | 60.1 | 29 | 10 |
| Reasoning | 63.1 | 23 | 8 |
| Math | 60.5 | 28 | 4 |
| Knowledge | 65.0 | 4 | 1 |
| Frontend | 60.0 | 20 | 3 |
| General | 62.4 | 15 | 5 |
| Multimodal | 61.3 | 11 | 1 |
| Value vs price | +11.8 | 19 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 63.6 ±1.8 | 12 |
| High | 58.8 ±3.5 | 4 |
| Low | 55.7 ±5.0 | 1 |
| Max | 61.4 ±1.0 | 26 |
| Medium | 57.1 ±5.0 | 1 |
| Minimal | 53.4 ±5.0 | 1 |
| Extra High | 59.2 ±1.7 | 21 |
Evidence
Coding 61.3 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 41.6% | Epoch AI | 2026-11-11 |
| FrontierSWE | 25.8% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Coding | 83.1% | LiveBench | 2026-11-06 |
| WeirdML v3 | 6.7% | Epoch AI | 2026-11-11 |
| MirrorCode | 54.4% | Epoch AI | 2026-10-20 |
| IOI | 56.6% | Vals AI | 2026-10-29 |
| SWE-bench Multimodal | 43.1% | Vals AI | 2026-11-09 |
| SciCode | 59.7% | Epoch AI | 2026-11-11 |
| ProgramBench | 2.5% | Vals AI | 2026-11-09 |
Agents 60.1 ±0.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 14.9% | Terminal-Bench | 2026-09-02 |
| SRE Bench | 3.8% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 10.0% | Vals AI | 2026-11-09 |
| APEX-Agents | 58.6% | Epoch AI | 2026-11-11 |
| Terminal-Bench 4.0 (Vals run) | 24.7% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Agentic | 47.9% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 30.9% | LiveBench | 2026-11-06 |
| Terminal-Bench 2.1 (Vals run) | 79.0% | Vals AI | 2026-10-01 |
| LiveBench 2.0 Research | 82.5% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 42.4% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 72.7% | Vals AI | 2026-11-05 |
Reasoning 63.1 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 85.1% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 36.0% | Vals AI | 2026-11-09 |
| CritPt | 26.0% | Epoch AI | 2026-11-11 |
| SimpleBench | 81.8% | SimpleBench | 2026-09-03 |
| Chess Puzzles | 37.0% | Epoch AI | 2026-10-13 |
| LiveBench 2.0 Reasoning | 89.7% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 25.0% | Epoch AI | 2026-09-18 |
| LiveBench 2.0 Data Analysis | 79.6% | LiveBench | 2026-11-06 |
Math 60.5 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 74.4% | Epoch AI | 2026-09-16 |
| FrontierMath Tier 4 | 46.3% | Epoch AI | 2026-09-18 |
| OTIS Mock AIME 2024-2025 | 99.2% | Epoch AI | 2026-09-17 |
| ProofBench v1.1 | 58.0% | Vals AI | 2026-11-09 |
| ProofBench | 58.0% | Epoch AI | 2026-11-11 |
Knowledge 65.0 ±6.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Legal Research Bench | 55.3% | Vals AI | 2026-11-09 |
Frontend 60.0 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 74.8% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 85.9% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,654 | LMArena | 2026-11-09 |
General 62.4 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,590 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 1,907 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,496 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 57.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 82.8% | EQ-Bench | 2026-11-11 |
Multimodal 61.3 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,291 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| APEX-Agents | 47.6% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 34.0% | Epoch AI | A stronger configuration result was used |
| CritPt | 24.9% | Epoch AI | A stronger configuration result was used |
| CursorBench | 37.5% | Epoch AI | A stronger configuration result was used |
| CursorBench | 33.4% | Epoch AI | A stronger configuration result was used |
| CursorBench | 32.6% | Epoch AI | A stronger configuration result was used |
| CursorBench | 29.3% | Epoch AI | A stronger configuration result was used |
| CursorBench | 24.3% | Epoch AI | A stronger configuration result was used |
| CyberBench v1.1 | 69.4% | Vals AI | A stronger configuration result was used |
| FrontierMath Tier 4 | 41.5% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 | 74.0% | Epoch AI | A stronger configuration result was used |
| IOI | 43.9% | Vals AI | A stronger configuration result was used |
| LMArena Vision | 1,288 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,621 | LMArena | A stronger configuration result was used |
| Legal Research Bench | 40.9% | Vals AI | A stronger configuration result was used |
| Mystery Game Puzzles | 14.1% | Epoch AI | A stronger configuration result was used |
| ProgramBench | 0.5% | Vals AI | A stronger configuration result was used |
| ProofBench | 55.0% | Epoch AI | A stronger configuration result was used |
| ProofBench v1.1 | 55.0% | Vals AI | A stronger configuration result was used |
| SciCode | 58.8% | Epoch AI | A stronger configuration result was used |
| Tax Agent Bench | 37.9% | Vals AI | A stronger configuration result was used |
| Terminal-Bench 2.1 (Vals run) | 72.3% | Vals AI | A stronger configuration result was used |
| Terminal-Bench 4.0 (Vals run) | 10.6% | Vals AI | A stronger configuration result was used |
| Terminal-Bench-Science | 4.3% | Vals AI | A stronger configuration result was used |
| Vibe Code Bench v1.1 | 82.9% | Vals AI | A stronger configuration result was used |
Names matched to this model
muse-spark-1-3, muse-spark-1-3-contributor