Gemini 3.8 Flash vs Muse Spark 1.1
Gemini 3.8 Flash 
Muse Spark 1.1 Verdict
- Muse Spark 1.1 leads on quality: 64.9 vs 63.5.
- Gemini 3.8 Flash (medium) is stronger in composite, knowledge, long context, multimodal.
- Muse Spark 1.1 is stronger in coding, agents & tools, human preference, instruction following, maths, reasoning.
- Gemini 3.8 Flash (medium) is 1.3× cheaper ($1.50 vs $2.00 per 1M blended).
- Gemini 3.8 Flash (medium) streams 1.4× faster (273 vs 194 tokens per second).
| Metric | Gemini 3.8 Flash (medium) | Muse Spark 1.1 |
|---|---|---|
| BenchLeader Index | 63.5 | 64.9 |
| Coding score | 63.6 | 68.2 |
| Composite score | 79.4 | 72.2 |
| Knowledge score | 77.6 | 73.1 |
| Long context score | 68.7 | 65.3 |
| Multimodal score | 68.9 | 64.9 |
| Agents & tools score | – | 62.7 |
| Human preference score | – | 66.0 |
| Instruction following score | – | 77.8 |
| Maths score | – | 52.2 |
| Reasoning score | – | 68.8 |
| Blended price $/M | $1.50 | $2.00 |
| Output speed | 273 tok/s | 194 tok/s |
| Time to first answer | 13.8 s | 2.0 s |
| Context window | 1M | 1.0M |
| SimpleQA Verified | – | 57.8% |
| SciCode | 54.4% | 58.2% |
| APEX-Agents | – | 41.9% |
| ProofBench | – | 39.0% |
| Epoch Capabilities Index | – | 154.6 |
| LMArena Text | – | 1492 |
| LMArena Hard Prompts | – | 1511 |
| LMArena Coding | – | 1531 |
| LMArena WebDev | – | 1541 |
| LMArena Vision | – | 1293 |
| LMArena Agent | – | -2.6 |
| AA Intelligence Index | 40 | 34.3 |
| AA-LCR | 84.0% | 77.7% |
| MMMU-Pro | 84.2% | – |
| AA-Omniscience | 28.6 | 28.1 |
| GPQA Diamond (AA) | 93.5% | 89.8% |
| Humanity's Last Exam (AA) | 42.1% | 46.2% |
| SciCode (AA) | 55.1% | 58.8% |
| SWE-Bench Pro | – | 61.5% |
| MCP Atlas | – | 88.1% |
| MultiChallenge | – | 75.3% |
| PRBench Finance | – | 55.0% |
| PRBench Legal | – | 57.0% |
| MultiNRC | – | 65.6% |
| EQ-Bench 4 | – | 1260 |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.