Up to four models
Muse Spark Open vs Gemini 3.1 Pro
On the index (GPT-4 = 100), Muse Spark Open scores 167 and Gemini 3.1 Pro 166. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Muse Spark Open167151–184
WeightsOpen
ReleasedOct 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken6 of 9
Gemini 3.1 Pro166150–183
WeightsClosed
ReleasedFeb 2026
Price in / out$2.0 / $12
Context1.05M
Core tests taken9 of 9
Muse Spark Open and Gemini 3.1 Pro are too close to call (1 point apart, within the uncertainty), ahead on 3 of 6 shared core tests, and costs 2.3× less.
Test by testthird-party results
Muse Spark OpenGemini 3.1 ProEvery result as a table
| Test | Muse Spark Open | Gemini 3.1 Pro |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 88.6% | 94.4% |
| SimpleQA Verified | 56.6% | 73.5% |
| Maths | ||
| FrontierMath (tiers 1-3) | 69.8% | 59.7% |
| AIME-style maths (OTIS mock) | 98.1% | 95.6% |
| FrontierMath (tier 4) | 31.7% | 26.8% |
| Coding | ||
| Terminal-Bench 4.0 | 6.6% | 2.5% |
| Code Migration | 21.2% | 17.3% |
| Vibe Code Bench v1.1 | 76.2% | 32.0% |
| Agents | ||
| APEX-Agents | 33.4% | 35.1% |
| Professional work | ||
| Finance Agent (v2) | 61.3% | 43.0% |
| EMB | 53.7% | 52.6% |
| Legal Research Bench | 38.5% | 20.7% |
| Tax Agent Bench | 26.3% | 9.3% |
| Novel problems | ||
| ARC-AGI-2 | 57.5% | 77.1% |
| ARC-AGI-1 | 89.0% | 98.0% |
Task length · METR46 sec
46 secTests at least two of these models have taken. Bold rows are the core tests.
