Muse Spark 1.1 vs Muse Spark 1.2
Muse Spark 1.1 Verdict
- Muse Spark 1.1 leads on quality: 64.9 vs 62.6.
- Muse Spark 1.1 is stronger in agents & tools, coding, human preference, instruction following, multimodal.
- Muse Spark 1.2 is stronger in composite, knowledge, long context, maths, reasoning.
- They cost about the same ($2.00 per 1M blended).
| Metric | Muse Spark 1.1 | Muse Spark 1.2 |
|---|---|---|
| BenchLeader Index | 64.9 | 62.6 |
| Agents & tools score | 62.7 | – |
| Coding score | 68.2 | 66.5 |
| Composite score | 72.2 | 79.1 |
| Human preference score | 66.0 | – |
| Instruction following score | 77.8 | – |
| Knowledge score | 73.1 | 76.9 |
| Long context score | 65.3 | 66.0 |
| Maths score | 52.2 | 54.3 |
| Multimodal score | 64.9 | – |
| Reasoning score | 68.8 | 70.2 |
| Blended price $/M | $2.00 | $2.00 |
| Output speed | 194 tok/s | 219 tok/s |
| Time to first answer | 2.0 s | 23.7 s |
| Context window | 1.0M | 1.0M |
| SimpleQA Verified | 57.8% | – |
| SimpleBench | – | 74.5% |
| SciCode | 58.2% | – |
| APEX-Agents | 41.9% | – |
| ProofBench | 39.0% | 43.0% |
| Epoch Capabilities Index | 154.6 | 155.5 |
| LMArena Text | 1492 | – |
| LMArena Hard Prompts | 1511 | – |
| LMArena Coding | 1531 | – |
| LMArena WebDev | 1541 | – |
| LMArena Vision | 1293 | – |
| LMArena Agent | -2.6 | – |
| AA Intelligence Index | 34.3 | 39.8 |
| AA-LCR | 77.7% | 79.0% |
| AA-Omniscience | 28.1 | 27.2 |
| GPQA Diamond (AA) | 89.8% | 90.4% |
| Humanity's Last Exam (AA) | 46.2% | 45.5% |
| SciCode (AA) | 58.8% | 57.4% |
| IOI | – | 49.5% |
| 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.