Introducing Muse Code and Muse Spark 1.2 5 Aug 2026
Muse Spark 1.2
Muse Spark 1.2 ranks first on 3 of the 54 benchmarks it has scores on.
55
Benchmarks with a score
3
Ranked first, out of five or more models
3
In the top three
Meta Aug 2026 Muse Spark 1.2
Closed weights Flagship
155.2
#38 of 271
Epoch Capabilities Index
- DeepSWE 54.9% #17 /28
- Harvey LAB (Legal Agent Benchmark) 25.4% #1 /80
- ProgramBench 0% #24 /25
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,492 | #11 of 333 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 81.5 | #12 of 119 | Official leaderboard | |
| Judgemark v4 | 79.4 | #6 of 40 | Official leaderboard | |
| SimpleQA Verified | 60.3% | #16 of 84 | Epoch AI | |
| Creative Writing v3 | 78.0 | #23 of 120 | Official leaderboard | |
| BullshitBench | 40% | #38 of 107 | Official leaderboard | |
| BullshitBench V2 | 50% | #44 of 122 | Official leaderboard | |
| Extended NYT Connections | 79.2% | #41 of 97 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ProofBench | 57% | #8 of 59 | Official leaderboard | |
| DTBench | 91.1% | #26 of 178 | Official leaderboard | |
| SimpleBench | 74.5% | #16 of 100 | Official leaderboard | |
| CritPt | 17.7% | #38 of 160 | Epoch AI | |
| ProofBench v1.1 | 43% | #33 of 51 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IOI (Vals) | 49.5% | #9 of 55 | Official leaderboard | |
| Vibe Code Bench | 79.1% | #29 of 115 | Official leaderboard | |
| WeirdML | 60.3% | #35 of 112 | Official leaderboard | |
| WebDev Arena | 1,534 | #35 of 105 | Epoch AI | |
| Code Arena | 1,534 | #46 of 124 | Official leaderboard | |
| Code Migration | 29.9% | #43 of 78 | Official leaderboard | |
| GameDevBench | 61% | #6 of 10 | Official leaderboard | |
| DeepSWE | 54.9% | #17 of 28 | Official leaderboard | |
| IOI v2 (Vals) | 21.8% | #42 of 45 | Official leaderboard | |
| FrontierSWE | 12% | #20 of 21 | Epoch AI | |
| ProgramBench | 0% | #24 of 25 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Toolathlon-Verified | 75.9% | #4 of 25 | Official leaderboard | |
| Terminal-Bench 2.1 | 82.9% | #20 of 53 | Model card | |
| Chess Puzzles | 27% | #50 of 83 | Epoch AI | |
| Agent Arena | -0.08 | #44 of 53 | Official leaderboard | |
| OSWorld 2.1 | 15.8% | #4 of 4 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TaxEval v2 | 80.4% | #1 of 129 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 25.4% | #1 of 80 | Official leaderboard | |
| CorpFin v2 | 70.9% | #5 of 119 | Official leaderboard | |
| Vals Finance Agent v2 | 60.6% | #4 of 80 | Official leaderboard | |
| MedScribe | 90.1% | #5 of 98 | Official leaderboard | |
| LegalBench | 85.3% | #23 of 138 | Official leaderboard | |
| Tax Agent Bench | 32.8% | #17 of 79 | Official leaderboard | |
| Public Benefits Bench | 68.5% | #11 of 50 | Official leaderboard | |
| MedCode | 49.4% | #24 of 96 | Official leaderboard | |
| Legal Research Bench | 43.8% | #24 of 88 | Official leaderboard | |
| MortgageTax | 65.4% | #40 of 86 | Official leaderboard | |
| Excel Modeling Benchmark | 57% | #44 of 76 | Official leaderboard | |
| Immigration Bench | 66.5% | #14 of 24 | Official leaderboard | |
| APEX-Agents | 45.4% | #38 of 56 | Epoch AI | |
| TaxCalcBench v2 | 20% | #20 of 26 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,293 | #9 of 136 | Official leaderboard | |
| GDP.pdf | 16% | #29 of 39 | Epoch AI | |
| Humanity's Sixth Sense | 24.5% | #25 of 29 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DistressBench | 88.4% | #1 of 42 | Official leaderboard | |
| CyberBench v1.1 (Vals) | 69.5% | #20 of 43 | Official leaderboard | |
| SRE-Bench | 0% | #33 of 33 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 77.4 | #20 of 150 | Official leaderboard | |
| Vals Multimodal Index | 69.8% | #6 of 33 | Official leaderboard | |
| Conceptual Reasoning Index | 62.7 | #29 of 149 | Official leaderboard | |
| LMCA | 48.4% | #31 of 139 | Epoch AI | |
| SAGE (Vals) | 47.7% | #30 of 81 | Official leaderboard |
Meta's models over time
Meta's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.