# MiMo-V2.5 vs Qwen3-30B-A3B

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 38.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiMo-V2.5 scores higher in 6 categories and Qwen3-30B-A3B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiMo-V2.5 leads 44.1 to 31.0.
- The biggest single-benchmark swing is SciCode: 43.1% for MiMo-V2.5 and 33.3% for Qwen3-30B-A3B.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 41K.

## Snapshot

| | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 38.5 |
| Rank | 89 | 174 |
| Context | 1.05M | 41K |
| Input $/M | $0.14 | $0.12 |
| Output $/M | $0.28 | $0.50 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.6 (#75)
- Qwen3-30B-A3B: 37.0 (#188)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 43.1% | 33.3% |
| LMArena Coding | 1469 | 1416 |
| LMArena WebDev | 1438 | — |
| WeirdML | — | 29.8% |
| ALE-Bench | 513.95 | — |

## Agentic & Tool Use

- MiMo-V2.5: —
- Qwen3-30B-A3B: 29.5 (#75)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |

## Reasoning

- MiMo-V2.5: 27.8 (#98)
- Qwen3-30B-A3B: 21.6 (#193)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 3.7% | 0.3% |
| LMArena Hard Prompts | 1450 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |

## Math

- MiMo-V2.5: 35.4 (#145)
- Qwen3-30B-A3B: 36.0 (#133)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1436 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| ProofBench | 16% | — |

## Knowledge

- MiMo-V2.5: 40.2 (#109)
- Qwen3-30B-A3B: 41.7 (#96)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1459 | 1395 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |

## Multimodal

- MiMo-V2.5: 39.0 (#53)
- Qwen3-30B-A3B: —

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- MiMo-V2.5: 52.0 (#96)
- Qwen3-30B-A3B: 49.8 (#126)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1404 | 1372 |
| LMArena Chinese | 1467 | 1434 |
| LMArena French | 1447 | 1419 |
| LMArena German | 1421 | 1379 |
| LMArena Japanese | 1304 | 1338 |
| LMArena Korean | 1363 | 1333 |
| LMArena Russian | 1395 | 1369 |
| LMArena Spanish | 1412 | 1403 |

## Instruction Following

- MiMo-V2.5: 75.7 (#55)
- Qwen3-30B-A3B: 72.2 (#137)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1364 |

## Long Context

- MiMo-V2.5: 44.1 (#69)
- Qwen3-30B-A3B: 31.0 (#278)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1444 | 1379 |
| Fiction.LiveBench | — | 40.6% |

## Writing & Preference

- MiMo-V2.5: 61.8 (#82)
- Qwen3-30B-A3B: 55.9 (#138)

| Benchmark | MiMo-V2.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1427 | 1384 |
| LMArena Creative Writing | 1392 | 1318 |
| LMArena Multi-Turn | 1445 | 1378 |
| Short-Story Creative Writing | — | 75.3% |

## FAQ

### Is MiMo-V2.5 better than Qwen3-30B-A3B?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 38.5 on the Noometry Index.

### Which is cheaper, MiMo-V2.5 or Qwen3-30B-A3B?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.

### Is MiMo-V2.5 or Qwen3-30B-A3B better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 37.0 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 41K.

### How many benchmarks do MiMo-V2.5 and Qwen3-30B-A3B share?

19 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen3-30B-A3B has 32.