Gemini 3.7 Flash vs Muse Spark 1.2
Gemini 3.7 Flash 
Muse Spark 1.2 Verdict
- Gemini 3.7 Flash (medium) leads on quality: 64.4 vs 62.6.
- Gemini 3.7 Flash (medium) is stronger in coding, long context, multimodal.
- Muse Spark 1.2 is stronger in composite, knowledge, reasoning, maths.
- Gemini 3.7 Flash (medium) is 1.3× cheaper ($1.50 vs $2.00 per 1M blended).
| Metric | Gemini 3.7 Flash (medium) | Muse Spark 1.2 |
|---|---|---|
| BenchLeader Index | 64.4 | 62.6 |
| Coding score | 68.3 | 66.5 |
| Composite score | 78.9 | 79.1 |
| Knowledge score | 75.2 | 76.9 |
| Long context score | 68.1 | 66.0 |
| Multimodal score | 69.4 | – |
| Reasoning score | 63.5 | 70.2 |
| Maths score | – | 54.3 |
| Blended price $/M | $1.50 | $2.00 |
| Output speed | 282 tok/s | 219 tok/s |
| Time to first answer | 5.3 s | 23.7 s |
| Context window | 1M | 1.0M |
| SimpleBench | – | 74.5% |
| SciCode | 57.9% | – |
| ProofBench | – | 43.0% |
| Epoch Capabilities Index | – | 155.5 |
| AA Intelligence Index | 39.6 | 39.8 |
| AA-LCR | 83.0% | 79.0% |
| MMMU-Pro | 84.7% | – |
| AA-Omniscience | 23.7 | 27.2 |
| GPQA Diamond (AA) | 92.1% | 90.4% |
| Humanity's Last Exam (AA) | 39.0% | 45.5% |
| SciCode (AA) | 59.8% | 57.4% |
| IOI | – | 49.5% |
| ARC-AGI-1 | 91.2% | – |
| ARC-AGI-2 | 63.8% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.