Model comparison
Claude Opus 4 vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Claude Opus 4 scores higher in 3 categories and MiMo-V2.5-Pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where MiMo-V2.5-Pro leads 55.1 to 48.8.
- The biggest single-benchmark swing is LMCA: 37.4% for Claude Opus 4 and 29.5% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 200K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 43.1 | 45.2 |
| Released | 2025-05-22 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 200K | 1.05M |
| Max output | 32K | 131K |
| Input $ / M tokens | $15 | $0.43 |
| Output $ / M tokens | $75 | $0.87 |
| Results tracked | 56 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4: 47.2 (#62), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1442 | 1503 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | — | 899.8 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Not comparable
Claude Opus 4: 34.8 (#42), MiMo-V2.5-Pro: —
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Too close to call
Claude Opus 4: 27.3 (#121), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0.3% | 4% |
| LMArena Hard Prompts | 1399 | 1488 |
| DTBench | 81.6% | 84.5% |
| LMCA | 37.4% | 29.5% |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 35.7% | — |
| EnigmaEval | 5.6% | — |
| Epoch Capabilities Index | 142.67 | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1390 | 1481 |
| OTIS Mock AIME 2024-2025 | 64.4% | — |
| ProofBench | — | 22% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1386 | 1503 |
| GPQA Diamond | 76.3% | — |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), MiMo-V2.5-Pro: —
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual MiMo-V2.5-Pro leads
Claude Opus 4: 48.8 (#138), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1362 | 1449 |
| LMArena Chinese | 1386 | 1507 |
| LMArena French | 1372 | 1488 |
| LMArena German | 1391 | 1458 |
| LMArena Japanese | 1331 | 1412 |
| LMArena Korean | 1321 | 1437 |
| LMArena Russian | 1392 | 1450 |
| LMArena Spanish | 1389 | 1471 |
Instruction Following Too close to call
Claude Opus 4: 77.1 (#28), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1406 | 1477 |
| IFEval | 91.8% | — |
Long Context MiMo-V2.5-Pro leads
Claude Opus 4: 39.6 (#172), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1422 | 1483 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference MiMo-V2.5-Pro leads
Claude Opus 4: 61.2 (#89), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Claude Opus 4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1377 | 1465 |
| LMArena Creative Writing | 1387 | 1440 |
| EQ-Bench Creative Writing | 1580 | 1493 |
| LMArena Multi-Turn | 1396 | 1477 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Claude Opus 4 better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or MiMo-V2.5-Pro better for coding?
They score almost the same on coding (47.2 vs 47.4); test both on your own repository before choosing.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4 and MiMo-V2.5-Pro share?
21 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and MiMo-V2.5-Pro has 27.