# MiMo-V2-Pro vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.5 to 42.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-pro-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. MiMo-V2-Pro scores higher in 3 categories and MiniMax-M3 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 40.8.
- The biggest single-benchmark swing is NYT Connections (extended): 25.8% for MiMo-V2-Pro and 65.1% for MiniMax-M3.
- Both cost about the same: $0.43 input and $0.87 output per million tokens.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 1M.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| Provider | Xiaomi | MiniMax |
| Noometry Index | 42.4 | 43.5 |
| Rank | 102 | 81 |
| Context | 1.05M | 1M |
| Input $/M | $0.43 | $0.30 |
| Output $/M | $0.87 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- MiMo-V2-Pro: 43.4 (#76)
- MiniMax-M3: 41.5 (#111)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1433 | 1482 |
| LMArena Coding | 1476 | 1470 |
| ALE-Bench | 785.17 | 640.02 |
| FrontierCode | — | 14.7% |
| SciCode | — | 47.1% |

## Agentic & Tool Use

- MiMo-V2-Pro: —
- MiniMax-M3: 22.5 (#121)

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

## Reasoning

- MiMo-V2-Pro: 21.3 (#200)
- MiniMax-M3: 29.3 (#83)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 25.8% | 65.1% |
| LMArena Hard Prompts | 1457 | 1447 |
| SimpleBench | — | 45.8% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Thematic Generalization | 45.9% | — |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 147 |
| ForecastBench | — | 61.4 |

## Math

- MiMo-V2-Pro: 36.7 (#104)
- MiniMax-M3: 39.1 (#83)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1447 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |

## Knowledge

- MiMo-V2-Pro: 40.8 (#106)
- MiniMax-M3: 58.4 (#32)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1479 | 1462 |
| GPQA Diamond | — | 90.9% |

## Multimodal

- MiMo-V2-Pro: —
- MiniMax-M3: 39.5 (#45)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |

## Multilingual

- MiMo-V2-Pro: 52.9 (#77)
- MiniMax-M3: 53.2 (#70)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1416 | 1420 |
| LMArena Chinese | 1455 | 1465 |
| LMArena French | 1470 | 1445 |
| LMArena German | 1417 | 1424 |
| LMArena Japanese | 1366 | 1381 |
| LMArena Korean | 1401 | 1372 |
| LMArena Russian | 1427 | 1430 |
| LMArena Spanish | 1458 | 1431 |

## Instruction Following

- MiMo-V2-Pro: 76.2 (#46)
- MiniMax-M3: 75.7 (#56)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1444 | 1433 |

## Long Context

- MiMo-V2-Pro: 41.5 (#133)
- MiniMax-M3: 44.2 (#68)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1455 | 1445 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |

## Writing & Preference

- MiMo-V2-Pro: 62.9 (#67)
- MiniMax-M3: 62.3 (#79)

| Benchmark | MiMo-V2-Pro | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1436 | 1433 |
| LMArena Creative Writing | 1415 | 1405 |
| LMArena Multi-Turn | 1456 | 1441 |
| EQ-Bench 4 | — | 1150 |

## FAQ

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

MiniMax-M3 is the stronger model overall, scoring 43.5 to 42.4 on the Noometry Index.

### Which is cheaper, MiMo-V2-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-Pro lists at $0.43 and $0.87.

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

MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

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

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

20 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and MiniMax-M3 has 41.