MiMo-V2.5-Pro vs Muse Spark
MiMo-V2.5-Pro 
Muse Spark Verdict
- Muse Spark leads on quality: 65.6 vs 59.1.
- MiMo-V2.5-Pro is stronger in long context.
- Muse Spark is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, maths, reasoning, multimodal.
| Metric | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| BenchLeader Index | 59.1 | 65.6 |
| Agents & tools score | 51.2 | 66.4 |
| Coding score | 58.4 | 66.2 |
| Composite score | 62.4 | 68.6 |
| Human preference score | 61.7 | 69.3 |
| Instruction following score | 77.0 | 79.7 |
| Knowledge score | 57.6 | 64.6 |
| Long context score | 66.4 | 65.5 |
| Maths score | 43.0 | 56.4 |
| Reasoning score | 67.5 | 70.2 |
| Multimodal score | – | 65.9 |
| Blended price $/M | $0.653 | – |
| Output speed | 36 tok/s | – |
| Time to first answer | 60.0 s | – |
| Context window | 1.0M | 262k |
| GPQA Diamond | – | 89.8% |
| OTIS Mock AIME | – | 88.9% |
| Humanity's Last Exam | – | 40.6% |
| SciCode | 50.2% | 51.5% |
| ProofBench | 22.0% | 17.0% |
| Epoch Capabilities Index | – | 152.1 |
| LMArena Text | 1468 | 1488 |
| LMArena Hard Prompts | 1496 | 1505 |
| LMArena Coding | 1521 | 1526 |
| LMArena WebDev | 1475 | – |
| LMArena Vision | – | 1306 |
| LMArena Agent | -5.1 | – |
| AA Intelligence Index | 26.4 | 31.3 |
| IFBench | 79.9% | 75.9% |
| AA-LCR | 79.7% | 78.0% |
| MMMU-Pro | – | 80.5% |
| AA-Omniscience | 3.3 | 7.2 |
| Terminal-Bench Hard | 43.2% | 45.5% |
| GPQA Diamond (AA) | 86.6% | 88.4% |
| Humanity's Last Exam (AA) | 35.7% | 40.7% |
| SciCode (AA) | 50.6% | – |
| τ²-Bench Telecom (AA) | 94.2% | 91.5% |
| AIME (Vals) | – | 96.9% |
| LiveCodeBench | 81.3% | – |
| MMLU-Pro | 84.6% | 87.3% |
| LegalBench | 77.1% | 84.2% |
| CorpFin | 61.4% | 65.1% |
| TaxEval | 73.8% | 77.7% |
| Terminal-Bench 2.1 (Vals) | 57.3% | – |
| SWE-bench (Vals) | 74.0% | 74.4% |
| GPQA Diamond (Vals) | 82.6% | 89.7% |
| Vals Index | 41.0 | – |
| SWE-Bench Pro | – | 55.0% |
| MCP Atlas | – | 82.2% |
| MultiChallenge | – | 75.5% |
| PRBench Finance | – | 52.4% |
| PRBench Legal | – | 52.3% |
| MultiNRC | – | 59.0% |
| TutorBench | – | 68.5% |
| EQ-Bench 4 | 1208 | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
MiMo-V2.5-Pro vs Muse Spark: questions
- Is MiMo-V2.5-Pro better than Muse Spark?
- Muse Spark leads on quality: 65.6 vs 59.1. The BenchLeader Index combines every independent quality benchmark; Muse Spark is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is MiMo-V2.5-Pro better than Muse Spark for coding?
- Muse Spark scores higher in coding (66 vs 58 on the category index, where 50 is average).
- Is MiMo-V2.5-Pro better than Muse Spark for agentic tasks?
- Muse Spark scores higher in agentic tasks (66 vs 51 on the category index, where 50 is average).
- Which has the larger context window?
- MiMo-V2.5-Pro accepts more context: 1.0M against 262k tokens.