Model comparison
Claude Sonnet 4 vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 40.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Claude Sonnet 4 scores higher in 1 category and MiMo-V2.6-Pro in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 22.9.
- The biggest single-benchmark swing is CritPt: 0.3% for Claude Sonnet 4 and 26.6% for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 200K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 40.8 | 50.3 |
| Released | 2025-05-22 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 200K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $0.43 |
| Output $ / M tokens | $15 | $0.87 |
| Results tracked | 58 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Claude Sonnet 4: 43.5 (#88), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| SciCode | 40% | 60.9% |
| LMArena Coding | 1414 | 1534 |
| ALE-Bench | 655.35 | 1,158 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1629 |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Too close to call
Claude Sonnet 4: 38.5 (#31), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning MiMo-V2.6-Pro leads
Claude Sonnet 4: 22.9 (#187), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 0.3% | 26.6% |
| LMArena Hard Prompts | 1372 | 1512 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math MiMo-V2.6-Pro leads
Claude Sonnet 4: 43.3 (#80), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1375 | 1494 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | — | 70% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge MiMo-V2.6-Pro leads
Claude Sonnet 4: 41.8 (#108), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1372 | 1543 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal MiMo-V2.6-Pro leads
Claude Sonnet 4: 26.2 (#121), MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1191 | 1264 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual MiMo-V2.6-Pro leads
Claude Sonnet 4: 46.7 (#156), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1333 | 1474 |
| LMArena Chinese | 1350 | 1529 |
| LMArena Russian | 1355 | 1480 |
| LMArena French | 1363 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1302 | — |
| LMArena Korean | 1291 | — |
| LMArena Spanish | 1357 | — |
Instruction Following MiMo-V2.6-Pro leads
Claude Sonnet 4: 71.7 (#145), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1376 | 1493 |
| IFEval | 84% | — |
Long Context MiMo-V2.6-Pro leads
Claude Sonnet 4: 33.7 (#259), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1398 | 1501 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference MiMo-V2.6-Pro leads
Claude Sonnet 4: 57.1 (#132), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Claude Sonnet 4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1351 | 1492 |
| LMArena Creative Writing | 1345 | 1468 |
| LMArena Multi-Turn | 1376 | 1464 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 40.8 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or MiMo-V2.6-Pro?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 43.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4 and MiMo-V2.6-Pro share?
16 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and MiMo-V2.6-Pro has 19.