# MiMo-V2.5-Pro vs o3-pro

> MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 42.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-pro-vs-o3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 3 categories and o3-pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 45.4.
- The biggest single-benchmark swing is LMCA: 29.5% for MiMo-V2.5-Pro and 38.5% for o3-pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $20 / $80 for o3-pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 200K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| Provider | Xiaomi | OpenAI |
| Noometry Index | 44.8 | 42.7 |
| Rank | 70 | 94 |
| Context | 1.05M | 200K |
| Input $/M | $0.43 | $20 |
| Output $/M | $0.87 | $80 |
| Weights | Open | Proprietary |

## Coding

- MiMo-V2.5-Pro: 47.0 (#58)
- o3-pro: 55.1 (#22)

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1477 | — |
| SciCode | 50.2% | — |
| WeirdML | — | 58.2% |
| LMArena Coding | 1502 | — |
| ALE-Bench | 899.8 | — |

## Reasoning

- MiMo-V2.5-Pro: 25.9 (#124)
- o3-pro: 24.1 (#152)

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| DTBench | 84.5% | 86.9% |
| LMCA | 29.5% | 38.5% |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 34.4% | — |
| ARC-AGI-1 | — | 59.3% |
| CritPt | 4% | — |
| LMArena Hard Prompts | 1487 | — |
| Epoch Capabilities Index | — | 147.43 |

## Math

- MiMo-V2.5-Pro: 38.6 (#84)
- o3-pro: —

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| ProofBench | 22% | — |
| LMArena Math | 1480 | — |

## Knowledge

- MiMo-V2.5-Pro: 41.5 (#100)
- o3-pro: 29.0 (#234)

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1501 | — |

## Multilingual

- MiMo-V2.5-Pro: 55.3 (#33)
- o3-pro: —

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| LMArena Non-English | 1449 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1489 | — |
| LMArena German | 1455 | — |
| LMArena Japanese | 1418 | — |
| LMArena Korean | 1436 | — |
| LMArena Russian | 1450 | — |
| LMArena Spanish | 1470 | — |

## Instruction Following

- MiMo-V2.5-Pro: 77.6 (#21)
- o3-pro: —

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1477 | — |

## Long Context

- MiMo-V2.5-Pro: 45.4 (#38)
- o3-pro: 72.1 (#1)

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1482 | — |

## Writing & Preference

- MiMo-V2.5-Pro: 65.5 (#47)
- o3-pro: 57.1 (#128)

| Benchmark | MiMo-V2.5-Pro | o3-pro |
|---|---|---|
| LMArena Text | 1465 | — |
| LMArena Creative Writing | 1440 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
| LMArena Multi-Turn | 1477 | — |

## FAQ

### Is MiMo-V2.5-Pro better than o3-pro?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 42.7 on the Noometry Index.

### Which is cheaper, MiMo-V2.5-Pro or o3-pro?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; o3-pro lists at $20 and $80.

### Is MiMo-V2.5-Pro or o3-pro better for coding?

o3-pro scores higher on coding benchmarks: 55.1 versus 47.0 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 200K.

### How many benchmarks do MiMo-V2.5-Pro and o3-pro share?

2 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and o3-pro has 12.