MiMo-V2.5-Pro vs Muse Spark 1.1
MiMo-V2.5-Pro 
Muse Spark 1.1 Verdict
- Muse Spark 1.1 leads on quality: 65.0 vs 59.1.
- MiMo-V2.5-Pro is stronger in long context.
- Muse Spark 1.1 is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, maths, reasoning, multimodal.
- MiMo-V2.5-Pro is 3.1× cheaper ($0.653 vs $2.00 per 1M blended).
- Muse Spark 1.1 streams 5.3× faster (194 vs 36 tokens per second).
| Metric | MiMo-V2.5-Pro | Muse Spark 1.1 |
|---|---|---|
| BenchLeader Index | 59.1 | 65.0 |
| Agents & tools score | 51.2 | 62.7 |
| Coding score | 58.4 | 68.1 |
| Composite score | 62.4 | 72.3 |
| Human preference score | 61.7 | 66.3 |
| Instruction following score | 77.0 | 77.8 |
| Knowledge score | 57.6 | 73.2 |
| Long context score | 66.4 | 65.4 |
| Maths score | 43.0 | 52.2 |
| Reasoning score | 67.5 | 69.2 |
| Multimodal score | – | 65.0 |
| Blended price $/M | $0.653 | $2.00 |
| Output speed | 36 tok/s | 194 tok/s |
| Time to first answer | 60.0 s | 2.6 s |
| Context window | 1.0M | 1.0M |
| SimpleQA Verified | – | 57.8% |
| SciCode | 50.2% | 58.2% |
| APEX-Agents | – | 41.9% |
| ProofBench | 22.0% | 39.0% |
| Epoch Capabilities Index | – | 154.6 |
| LMArena Text | 1468 | 1492 |
| LMArena Hard Prompts | 1496 | 1511 |
| LMArena Coding | 1521 | 1531 |
| LMArena WebDev | 1475 | 1541 |
| LMArena Vision | – | 1293 |
| LMArena Agent | -5.1 | -2.6 |
| AA Intelligence Index | 26.4 | 34.3 |
| IFBench | 79.9% | – |
| AA-LCR | 79.7% | 77.7% |
| AA-Omniscience | 3.3 | 28.1 |
| Terminal-Bench Hard | 43.2% | – |
| GPQA Diamond (AA) | 86.6% | 89.8% |
| Humanity's Last Exam (AA) | 35.7% | 46.2% |
| SciCode (AA) | 50.6% | 58.8% |
| τ²-Bench Telecom (AA) | 94.2% | – |
| LiveCodeBench | 81.3% | – |
| MMLU-Pro | 84.6% | – |
| LegalBench | 77.1% | – |
| CorpFin | 61.4% | – |
| TaxEval | 73.8% | – |
| Terminal-Bench 2.1 (Vals) | 57.3% | – |
| SWE-bench (Vals) | 74.0% | – |
| GPQA Diamond (Vals) | 82.6% | – |
| Vals Index | 41.0 | – |
| 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 | 1208 | 1260 |
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 1.1: questions
- Is MiMo-V2.5-Pro better than Muse Spark 1.1?
- Muse Spark 1.1 leads on quality: 65.0 vs 59.1. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.1 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 1.1 for coding?
- Muse Spark 1.1 scores higher in coding (68 vs 58 on the category index, where 50 is average).
- Is MiMo-V2.5-Pro better than Muse Spark 1.1 for agentic tasks?
- Muse Spark 1.1 scores higher in agentic tasks (63 vs 51 on the category index, where 50 is average).
- Which is cheaper, MiMo-V2.5-Pro or Muse Spark 1.1?
- MiMo-V2.5-Pro is cheaper: $0.653 against $2.00 per million tokens, blended at three input tokens per output token.
- Which is faster, MiMo-V2.5-Pro or Muse Spark 1.1?
- Muse Spark 1.1 streams faster: 194 against 36 output tokens per second.
- Which has the larger context window?
- Both accept 1.0M tokens of context.