Model comparison
Claude Sonnet 4.5 vs MiMo-V2-Pro
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 11× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and MiMo-V2-Pro in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2-Pro leads 39.5 to 32.3.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 25.8% for MiMo-V2-Pro.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4.5 | MiMo-V2-Pro | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 44.1 | 43.0 |
| Released | 2025-09-29 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $0.43 |
| Output $ / M tokens | $15 | $0.87 |
| Results tracked | 73 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1393 | 1433 |
| LMArena Coding | 1489 | 1476 |
| ALE-Bench | 796.15 | 785.17 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.5: 38.3 (#32), MiMo-V2-Pro: —
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#125), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 37.3% | 25.8% |
| LMArena Hard Prompts | 1462 | 1457 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| Thematic Generalization | — | 45.9% |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
Math MiMo-V2-Pro leads
Claude Sonnet 4.5: 32.3 (#216), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1449 | 1447 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1482 | 1478 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), MiMo-V2-Pro: —
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Too close to call
Claude Sonnet 4.5: 53.4 (#69), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1425 | 1416 |
| LMArena Chinese | 1459 | 1456 |
| LMArena French | 1458 | 1469 |
| LMArena German | 1427 | 1417 |
| LMArena Japanese | 1390 | 1366 |
| LMArena Korean | 1403 | 1400 |
| LMArena Russian | 1437 | 1427 |
| LMArena Spanish | 1457 | 1457 |
Instruction Following MiMo-V2-Pro leads
Claude Sonnet 4.5: 75.0 (#78), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1459 | 1445 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1476 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Claude Sonnet 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1439 | 1436 |
| LMArena Creative Writing | 1442 | 1415 |
| LMArena Multi-Turn | 1465 | 1456 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than MiMo-V2-Pro?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 11× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.5 or MiMo-V2-Pro?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or MiMo-V2-Pro better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 43.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4.5 and MiMo-V2-Pro share?
20 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and MiMo-V2-Pro has 23.