MiMo-V2.5 vs Muse Spark 1.3
MiMo-V2.5 
Muse Spark 1.3 Verdict
- Muse Spark 1.3 leads on quality: 68.3 vs 58.6.
- MiMo-V2.5 is stronger in agents & tools, instruction following, multimodal.
- Muse Spark 1.3 is stronger in composite, knowledge, long context.
- MiMo-V2.5 is 11× cheaper ($0.175 vs $2.00 per 1M blended).
- Muse Spark 1.3 streams 5.3× faster (241 vs 45 tokens per second).
| Metric | MiMo-V2.5 | Muse Spark 1.3 |
|---|---|---|
| BenchLeader Index | 58.6 | 68.3 |
| Agents & tools score | 70.4 | – |
| Composite score | 57.4 | 90.3 |
| Instruction following score | 66.5 | – |
| Knowledge score | 59.7 | 79.1 |
| Long context score | 63.1 | 68.2 |
| Multimodal score | 60.1 | – |
| Blended price $/M | $0.175 | $2.00 |
| Output speed | 45 tok/s | 241 tok/s |
| Time to first answer | 50.4 s | 30.5 s |
| Context window | 1M | 1.0M |
| AA Intelligence Index | 22.3 | 48.2 |
| IFBench | 67.1% | – |
| AA-LCR | 73.0% | 83.0% |
| MMMU-Pro | 75.4% | – |
| AA-Omniscience | -9.8 | 25 |
| Terminal-Bench Hard | 41.7% | – |
| GPQA Diamond (AA) | 85.0% | 93.5% |
| Humanity's Last Exam (AA) | 27.2% | 48.7% |
| SciCode (AA) | 43.9% | 58.8% |
| τ²-Bench Telecom (AA) | 90.6% | – |
| PRBench Finance | – | 59.5% |
| PRBench Legal | – | 61.6% |
Data as of 2026-09-14. Best configuration of each model; every score links to its source on the model pages.
MiMo-V2.5 vs Muse Spark 1.3: questions
- Is MiMo-V2.5 better than Muse Spark 1.3?
- Muse Spark 1.3 leads on quality: 68.3 vs 58.6. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 is ahead overall as of 2026-09-14, but check the category scores for your use.
- Which is cheaper, MiMo-V2.5 or Muse Spark 1.3?
- MiMo-V2.5 is cheaper: $0.175 against $2.00 per million tokens, blended at three input tokens per output token.
- Which is faster, MiMo-V2.5 or Muse Spark 1.3?
- Muse Spark 1.3 streams faster: 241 against 45 output tokens per second.
- Which has the larger context window?
- Muse Spark 1.3 accepts more context: 1.0M against 1M tokens.