Up to four models
Muse Spark 1.2 vs Gemini 3.1 Pro
On the index (GPT-4 = 100), Muse Spark 1.2 scores 162 and Gemini 3.1 Pro 161. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
162146–178
WeightsClosed
ReleasedAug 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken3 of 9
161146–177
WeightsClosed
ReleasedFeb 2026
Price in / out$2.0 / $12
Context1.05M
Core tests taken9 of 9
Muse Spark 1.2 and Gemini 3.1 Pro are too close to call (1 point apart, within the uncertainty), ahead on 3 of 3 shared core tests, and costs 2.3× less.
Test by testthird-party results
Every result as a table
| Test | Muse Spark 1.2 | Gemini 3.1 Pro |
|---|---|---|
| Reasoning & knowledge | ||
| MMLU Pro | 88.3% | 91.0% |
| MMMU Pro | 86.1% | 88.2% |
| SimpleBench | 74.5% | 79.6% |
| SimpleQA Verified | 60.3% | 73.5% |
| Maths | ||
| ProofBench v1.1 | 43.0% | 26.0% |
| Chess puzzles | 27.0% | 51.0% |
| Coding | ||
| Terminal-Bench 4.0 | 6.1% | 2.5% |
| Code Migration | 29.9% | 17.3% |
| IOI | 21.8% | 51.8% |
| ProgramBench | 0.5% | 0.0% |
| SWE-bench | 86.6% | 78.8% |
| Vibe Code Bench v1.1 | 79.1% | 32.0% |
| DeepSWE | 54.9% | 11.7% |
| WeirdML | 60.4% | 72.1% |
| Agents | ||
| APEX-Agents | 45.4% | 35.1% |
| BioMysteryBench | 64.8% | 60.0% |
| SRE Bench | 0.0% | 0.0% |
| DTBench | 94.7% | 97.1% |
| LMCA | 48.4% | 53.8% |
| Professional work | ||
| Finance Agent (v2) | 60.6% | 43.0% |
| CorpFin v2 | 70.9% | 64.5% |
| EMB | 57.0% | 52.6% |
| LegalBench | 85.3% | 87.4% |
| Legal Research Bench | 43.8% | 20.7% |
| MedCode | 49.4% | 59.1% |
| MedScribe | 90.1% | 76.1% |
| MortgageTax | 65.4% | 69.4% |
| Public Benefits Bench v1.1 | 68.5% | 53.8% |
| Tax Agent Bench | 32.8% | 9.3% |
| TaxEval v2 | 80.4% | 72.9% |
Task length · METR
46 sec
Tests at least two of these models have taken. Bold rows are the core tests.