# MiMo-V2.5 vs Qwen3 235B-A22B

> MiMo-V2.5 and Qwen3 235B-A22B score almost the same on the Noometry Index (43.0 vs 43.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-qwen3-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiMo-V2.5 scores higher in 3 categories and Qwen3 235B-A22B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 35.4.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 43.2 |
| Rank | 89 | 83 |
| Context | 1.05M | 131K |
| Input $/M | $0.14 | $0.70 |
| Output $/M | $0.28 | $2.80 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.6 (#75)
- Qwen3 235B-A22B: 43.8 (#72)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 43.1% | 42.4% |
| LMArena Coding | 1469 | 1445 |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1438 | — |
| WeirdML | — | 41% |
| ALE-Bench | 513.95 | — |

## Agentic & Tool Use

- MiMo-V2.5: —
- Qwen3 235B-A22B: 33.7 (#48)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |

## Reasoning

- MiMo-V2.5: 27.8 (#98)
- Qwen3 235B-A22B: 15.8 (#302)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| CritPt | 3.7% | 0% |
| LMArena Hard Prompts | 1450 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |

## Math

- MiMo-V2.5: 35.4 (#145)
- Qwen3 235B-A22B: 48.5 (#51)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1436 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | 16% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- MiMo-V2.5: 40.2 (#109)
- Qwen3 235B-A22B: 49.5 (#67)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Expert | 1459 | 1460 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |

## Multimodal

- MiMo-V2.5: 39.0 (#53)
- Qwen3 235B-A22B: —

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- MiMo-V2.5: 52.0 (#96)
- Qwen3 235B-A22B: 52.5 (#84)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1404 | 1410 |
| LMArena Chinese | 1467 | 1481 |
| LMArena French | 1447 | 1445 |
| LMArena German | 1421 | 1432 |
| LMArena Japanese | 1304 | 1400 |
| LMArena Korean | 1363 | 1391 |
| LMArena Russian | 1395 | 1411 |
| LMArena Spanish | 1412 | 1429 |

## Instruction Following

- MiMo-V2.5: 75.7 (#55)
- Qwen3 235B-A22B: 72.8 (#132)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1408 |
| IFEval | — | 83.5% |

## Long Context

- MiMo-V2.5: 44.1 (#69)
- Qwen3 235B-A22B: 46.1 (#25)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1444 | 1426 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- MiMo-V2.5: 61.8 (#82)
- Qwen3 235B-A22B: 59.8 (#103)

| Benchmark | MiMo-V2.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1427 | 1419 |
| LMArena Creative Writing | 1392 | 1384 |
| LMArena Multi-Turn | 1445 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |

## FAQ

### Is MiMo-V2.5 better than Qwen3 235B-A22B?

MiMo-V2.5 and Qwen3 235B-A22B score almost the same on the Noometry Index (43.0 vs 43.2), so choose on price, context window or the category you care about most.

### Which is cheaper, MiMo-V2.5 or Qwen3 235B-A22B?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.

### Is MiMo-V2.5 or Qwen3 235B-A22B better for coding?

They score almost the same on coding (43.6 vs 43.8); test both on your own repository before choosing.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 131K.

### How many benchmarks do MiMo-V2.5 and Qwen3 235B-A22B share?

19 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen3 235B-A22B has 49.