# MiMo-V2.5-Pro vs MiniMax-M3

> MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-pro-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 5 categories and MiniMax-M3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 42.2.
- The biggest single-benchmark swing is NYT Connections (extended): 34.4% for MiMo-V2.5-Pro and 65.1% for MiniMax-M3.
- Both cost about the same: $0.43 input and $0.87 output per million tokens.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| Provider | Xiaomi | MiniMax |
| Noometry Index | 45.2 | 43.8 |
| Rank | 74 | 85 |
| Context | 1.05M | 1M |
| Input $/M | $0.43 | $0.30 |
| Output $/M | $0.87 | $1.20 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5-Pro: 47.4 (#60)
- MiniMax-M3: 41.8 (#118)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1479 | 1482 |
| SciCode | 50.2% | 47.1% |
| LMArena Coding | 1503 | 1469 |
| ALE-Bench | 899.8 | 640.02 |
| FrontierCode | — | 14.7% |

## Agentic & Tool Use

- MiMo-V2.5-Pro: —
- MiniMax-M3: 22.6 (#130)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- MiMo-V2.5-Pro: 26.8 (#130)
- MiniMax-M3: 30.1 (#87)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 34.4% | 65.1% |
| CritPt | 4% | 3.7% |
| LMArena Hard Prompts | 1488 | 1447 |
| DTBench | 84.5% | 78.9% |
| LMCA | 29.5% | 33.7% |
| SimpleBench | — | 45.8% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |

## Math

- MiMo-V2.5-Pro: 40.0 (#96)
- MiniMax-M3: 40.0 (#95)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| ProofBench | 22% | 18% |
| LMArena Math | 1481 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |

## Knowledge

- MiMo-V2.5-Pro: 42.2 (#98)
- MiniMax-M3: 58.4 (#35)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1503 | 1461 |
| GPQA Diamond | — | 90.9% |

## Multimodal

- MiMo-V2.5-Pro: —
- MiniMax-M3: 40.2 (#51)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- MiMo-V2.5-Pro: 55.1 (#34)
- MiniMax-M3: 53.0 (#75)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1449 | 1420 |
| LMArena Chinese | 1507 | 1463 |
| LMArena French | 1488 | 1447 |
| LMArena German | 1458 | 1426 |
| LMArena Japanese | 1412 | 1381 |
| LMArena Korean | 1437 | 1372 |
| LMArena Russian | 1450 | 1428 |
| LMArena Spanish | 1471 | 1432 |

## Instruction Following

- MiMo-V2.5-Pro: 77.5 (#21)
- MiniMax-M3: 75.5 (#62)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1477 | 1433 |

## Long Context

- MiMo-V2.5-Pro: 45.4 (#37)
- MiniMax-M3: 44.2 (#72)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1483 | 1445 |

## Writing & Preference

- MiMo-V2.5-Pro: 65.3 (#49)
- MiniMax-M3: 62.1 (#83)

| Benchmark | MiMo-V2.5-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1465 | 1433 |
| LMArena Creative Writing | 1440 | 1404 |
| EQ-Bench 4 | 1208 | 1150 |
| LMArena Multi-Turn | 1477 | 1442 |
| EQ-Bench Creative Writing | 1493 | — |

## FAQ

### Is MiMo-V2.5-Pro better than MiniMax-M3?

MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.8 on the Noometry Index.

### Which is cheaper, MiMo-V2.5-Pro or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.

### Is MiMo-V2.5-Pro or MiniMax-M3 better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 1M.

### How many benchmarks do MiMo-V2.5-Pro and MiniMax-M3 share?

26 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and MiniMax-M3 has 41.