MiMo-V2.6-Pro vs Muse Spark 1.3
MiMo-V2.6-Pro 
Muse Spark 1.3 Verdict
- Muse Spark 1.3 (max) leads on quality: 68.9 vs 64.3.
- MiMo-V2.6-Pro is stronger in long context, reasoning.
- Muse Spark 1.3 (max) is stronger in agents & tools, composite, knowledge, coding, human preference, maths, multimodal.
- MiMo-V2.6-Pro is 3.6× cheaper ($0.548 vs $2.00 per 1M blended).
- Muse Spark 1.3 (max) streams 4.1× faster (219 vs 54 tokens per second).
| Metric | MiMo-V2.6-Pro | Muse Spark 1.3 (max) |
|---|---|---|
| BenchLeader Index | 64.3 | 68.9 |
| Agents & tools score | 55.1 | 70.8 |
| Composite score | 84.8 | 86.9 |
| Knowledge score | 66.8 | 74.4 |
| Long context score | 69.1 | 67.3 |
| Reasoning score | 88.8 | 80.3 |
| Coding score | – | 66.8 |
| Human preference score | – | 69.8 |
| Maths score | – | 65.9 |
| Multimodal score | – | 67.4 |
| Blended price $/M | $0.548 | $2.00 |
| Output speed | 54 tok/s | 219 tok/s |
| Time to first answer | 39.8 s | 30.1 s |
| Context window | 1.0M | 1.0M |
| FrontierMath Tiers 1–3 | – | 74.0% |
| FrontierMath Tier 4 | – | 46.3% |
| SciCode | – | 58.8% |
| LMArena Text | – | 1493 |
| LMArena Hard Prompts | – | 1516 |
| LMArena Coding | – | 1537 |
| LMArena WebDev | – | 1657 |
| LMArena Vision | – | 1315 |
| LMArena Agent | – | 4.2 |
| AA Intelligence Index | 46.3 | 48.1 |
| AA-LCR | 86.3% | 83.0% |
| AA-Omniscience | 8.4 | 25 |
| GPQA Diamond (AA) | – | 93.5% |
| Humanity's Last Exam (AA) | 49.4% | 48.7% |
| SciCode (AA) | 60.9% | 58.8% |
| IOI | – | 56.6% |
| Terminal-Bench 2.1 (Vals) | 67.8% | 79.0% |
| Vals Index | 59.7 | 64.5 |
| CritPt | 26.6% | 24.9% |
| GDPval (AA) | 58.7% | 58.7% |
| τ²-Bench Banking (AA) | – | 50.5% |
| Code Migration | 43.0% | 47.4% |
| CyberBench | – | 72.7% |
| Excel Modeling Benchmark | 62.9% | 67.4% |
| Finance Agent v2 | 58.3% | 60.0% |
| Harvey's Legal Agent Benchmark | 10.8% | 23.8% |
| Legal Research Bench | 47.1% | 55.3% |
| MysteryMechanism | – | 36.0% |
| Terminal-Bench 4.0 (Vals) | – | 27.8% |
| Terminal-Bench Science | 2.9% | 14.3% |
| Vibe Code Bench 1-100 | – | 20.5% |
| Vibe Code Bench v1.1 | 85.2% | 85.9% |
| LMArena Maths | – | 1496 |
| LMArena Creative Writing | – | 1453 |
| LMArena Instruction Following | – | 1483 |
| LMArena Multi-turn | – | 1493 |
| LMArena Longer Queries | – | 1506 |
| LMArena Document | – | 1468 |
| Chess Puzzles | – | 38.0% |
| Mystery Game Puzzles | – | 25.0% |
| CursorBench | – | 41.6% |
| Terminal-Bench 4.0 (AA) | 34.9% | 33.3% |
| Terminal-Bench 2.1 (AA) | – | 84.3% |
| AutomationBench | 58.6% | 57.9% |
| GDP.pdf | 19.2% | 26.6% |
| MLCR | – | 43.3% |
| AA-Omniscience: accuracy | 34.9% | 43.6% |
| AA-Omniscience: non-hallucination | 59.4% | 67.1% |
| AA-Briefcase | 1522 | 1597 |
Data as of 2026-09-23. Best configuration of each model; every score links to its source on the model pages.
MiMo-V2.6-Pro vs Muse Spark 1.3: questions
- Is MiMo-V2.6-Pro better than Muse Spark 1.3?
- Muse Spark 1.3 (max) leads on quality: 68.9 vs 64.3. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 (max) is ahead overall as of 2026-09-23, but check the category scores for your use.
- Is MiMo-V2.6-Pro better than Muse Spark 1.3 for agentic tasks?
- Muse Spark 1.3 scores higher in agentic tasks (71 vs 55 on the category index, where 50 is average).
- Which is cheaper, MiMo-V2.6-Pro or Muse Spark 1.3?
- MiMo-V2.6-Pro is cheaper: $0.548 against $2.00 per million tokens, blended at three input tokens per output token.
- Which is faster, MiMo-V2.6-Pro or Muse Spark 1.3?
- Muse Spark 1.3 streams faster: 219 against 54 output tokens per second.
- Which has the larger context window?
- Both accept 1.0M tokens of context.