Gemini 3.5 Flash vs Muse Spark 1.2
Gemini 3.5 Flash 
Muse Spark 1.2 Verdict
- Gemini 3.5 Flash (medium) leads on quality: 63.9 vs 62.6.
- Gemini 3.5 Flash (medium) is stronger in agents & tools, human preference, instruction following, multimodal.
- Muse Spark 1.2 is stronger in coding, composite, knowledge, long context, reasoning, maths.
- Muse Spark 1.2 is 1.7× cheaper ($2.00 vs $3.38 per 1M blended).
| Metric | Gemini 3.5 Flash (medium) | Muse Spark 1.2 |
|---|---|---|
| BenchLeader Index | 63.9 | 62.6 |
| Agents & tools score | 67.8 | – |
| Coding score | 58.9 | 66.5 |
| Composite score | 71.4 | 79.1 |
| Human preference score | 67.4 | – |
| Instruction following score | 72.2 | – |
| Knowledge score | 73.9 | 76.9 |
| Long context score | 63.6 | 66.0 |
| Multimodal score | 67.6 | – |
| Reasoning score | 66.8 | 70.2 |
| Maths score | – | 54.3 |
| Blended price $/M | $3.38 | $2.00 |
| Output speed | 209 tok/s | 219 tok/s |
| Time to first answer | 17.0 s | 23.7 s |
| Context window | 1M | 1.0M |
| SimpleBench | – | 74.5% |
| ProofBench | – | 43.0% |
| Epoch Capabilities Index | – | 155.5 |
| LMArena Text | 1476 | – |
| LMArena Hard Prompts | 1493 | – |
| LMArena Coding | 1503 | – |
| LMArena WebDev | 1491 | – |
| LMArena Vision | 1306 | – |
| AA Intelligence Index | 33.6 | 39.8 |
| IFBench | 74.6% | – |
| AA-LCR | 74.3% | 79.0% |
| MMMU-Pro | 83.9% | – |
| AA-Omniscience | 20.8 | 27.2 |
| Terminal-Bench Hard | 39.4% | – |
| GPQA Diamond (AA) | 92.1% | 90.4% |
| Humanity's Last Exam (AA) | 41.3% | 45.5% |
| SciCode (AA) | – | 57.4% |
| τ²-Bench Telecom (AA) | 95.6% | – |
| IOI | – | 49.5% |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.