MiMo-V2.6-Flash vs Muse Spark 1.3
MiMo-V2.6-Flash 
Muse Spark 1.3 Verdict
- Muse Spark 1.3 (max) leads on quality: 67.7 vs 59.7.
- Muse Spark 1.3 (max) is stronger in agents & tools, coding, composite, human preference, knowledge, long context, maths, multimodal, reasoning.
- MiMo-V2.6-Flash is 11× cheaper ($0.175 vs $2.00 per 1M blended).
- Muse Spark 1.3 (max) streams 3.0× faster (175 vs 58 tokens per second).
| Metric | MiMo-V2.6-Flash | Muse Spark 1.3 (max) |
|---|---|---|
| BenchLeader Index | 59.7 | 67.7 |
| Agents & tools score | 55.5 | 70.3 |
| Coding score | 60.1 | 64.6 |
| Composite score | 72.5 | 84.1 |
| Human preference score | 64.0 | 69.4 |
| Knowledge score | 56.0 | 72.9 |
| Long context score | 62.3 | 66.8 |
| Maths score | 63.4 | 63.6 |
| Multimodal score | 57.8 | 65.9 |
| Reasoning score | 62.5 | 78.1 |
| Blended price $/M | $0.175 | $2.00 |
| Output speed | 58 tok/s | 175 tok/s |
| Time to first answer | 38.1 s | 70.5 s |
| Context window | 1.0M | 1.0M |
| FrontierMath Tiers 1–3 | – | 74.0% |
| FrontierMath Tier 4 | – | 46.3% |
| SciCode | 51.3% | 58.8% |
| ProofBench | 63.0% | 58.0% |
| LMArena Text | 1451 | 1494 |
| LMArena Hard Prompts | 1484 | 1517 |
| LMArena Coding | 1514 | 1538 |
| LMArena WebDev | 1637 | 1657 |
| LMArena Vision | 1259 | 1309 |
| LMArena Agent | 0.4 | 4 |
| AA Intelligence Index v4.3.2 | 37.9 | 48.1 |
| AA-LCR | 74.3% | 83.0% |
| MMMU-Pro | 73.1% | – |
| AA-Omniscience | -12.7 | 25 |
| GPQA Diamond (AA) | – | 93.5% |
| Humanity's Last Exam (AA) | 35.1% | 48.7% |
| SciCode (AA) | 51.3% | 58.8% |
| IOI | 47.7% | 56.6% |
| Terminal-Bench 2.1 (Vals) | 76.4% | 79.0% |
| Vals Index | 53.2 | 58.2 |
| CritPt | 12.0% | 24.9% |
| GDPval-AA v2.1 | 55.5% | 59.0% |
| τ³-Banking (AA) | – | 50.5% |
| ITBench SRE (AA) | – | 33.2% |
| BioMysteryBench | 69.3% | – |
| Code Migration | 40.9% | 47.4% |
| CUA-bench | – | 5.8% |
| CyberBench | 75.4% | 72.7% |
| Excel Modeling Benchmark | 65.5% | 67.4% |
| Finance Agent v2 | 56.3% | 60.0% |
| Harvey's Legal Agent Benchmark | 11.3% | 23.8% |
| Legal Research Bench | 38.0% | 55.3% |
| MedCode | 41.1% | – |
| MedScribe | 85.3% | – |
| MysteryMechanism | 21.6% | 36.0% |
| ProgramBench | 0.5% | – |
| Public Benefits Bench | 67.6% | – |
| SAGE | 43.5% | – |
| SREBench | 4.2% | – |
| Tax Agent Bench | 59.9% | 72.4% |
| Terminal-Bench 4.0 (Vals) | 24.2% | 24.8% |
| Terminal-Bench Science | 4.3% | 10.0% |
| Vibe Code Bench 1-100 | – | 20.5% |
| Vibe Code Bench v1.1 | 79.0% | 85.9% |
| LMArena Maths | 1462 | 1502 |
| LMArena Creative Writing | 1387 | 1456 |
| LMArena Instruction Following | 1451 | 1483 |
| LMArena Multi-turn | 1452 | 1487 |
| LMArena Longer Queries | 1463 | 1497 |
| LMArena Document | – | 1468 |
| Chess Puzzles | – | 38.0% |
| Mystery Game Puzzles | – | 25.0% |
| CursorBench | – | 41.6% |
| Terminal-Bench 4.0 (AA) | 22.7% | 33.3% |
| Terminal-Bench 2.1 (AA) | – | 84.3% |
| AutomationBench | – | 57.9% |
| GDP.pdf | – | 26.6% |
| MLCR | – | 43.3% |
| Harvey LAB | – | 8.9% |
| AA-Omniscience: accuracy | 27.0% | 43.6% |
| AA-Omniscience: non-hallucination | 45.6% | 67.1% |
| AA-Briefcase v1.1 | – | 1581 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
MiMo-V2.6-Flash vs Muse Spark 1.3: questions
- Is MiMo-V2.6-Flash better than Muse Spark 1.3?
- Muse Spark 1.3 (max) leads on quality: 67.7 vs 59.7. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is MiMo-V2.6-Flash better than Muse Spark 1.3 for coding?
- Muse Spark 1.3 scores higher in coding (65 vs 60 on the category index, where 50 is average).
- Is MiMo-V2.6-Flash better than Muse Spark 1.3 for agentic tasks?
- Muse Spark 1.3 scores higher in agentic tasks (70 vs 56 on the category index, where 50 is average).
- Which is cheaper, MiMo-V2.6-Flash or Muse Spark 1.3?
- MiMo-V2.6-Flash is cheaper: $0.175 against $2.00 per million tokens, blended at three input tokens per output token.
- Which is faster, MiMo-V2.6-Flash or Muse Spark 1.3?
- Muse Spark 1.3 streams faster: 175 against 58 output tokens per second.
- Which has the larger context window?
- Both accept 1.0M tokens of context.