# Mistral Large 3 vs o1-pro

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-3-vs-o1-pro
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Mistral Large 3 leads 35.5 to 29.3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $150 / $600 for o1-pro.
- Mistral Large 3 accepts more context: 262K tokens versus 200K.
- Mistral Large 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Large 3 | o1-pro |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 38.6 | 31.2 |
| Rank | 172 | 264 |
| Context | 262K | 200K |
| Input $/M | $0.25 | $150 |
| Output $/M | $0.75 | $600 |
| Weights | Open | Proprietary |

## Coding

- Mistral Large 3: 34.1 (#230)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena WebDev | 1230 | — |
| LMArena Coding | 1447 | — |

## Reasoning

- Mistral Large 3: 14.6 (#314)
- o1-pro: 20.2 (#223)

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| ARC-AGI-1 | — | 23.3% |
| EnigmaEval | — | 6.1% |
| Thematic Generalization | 23% | — |
| LMArena Hard Prompts | 1429 | — |

## Math

- Mistral Large 3: 36.0 (#131)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena Math | 1415 | — |

## Knowledge

- Mistral Large 3: 35.5 (#173)
- o1-pro: 29.3 (#227)

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| Vectara Hallucination Rate | 14.5% | — |
| LMArena Expert | 1421 | — |

## Multimodal

- Mistral Large 3: 37.6 (#65)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Large 3: 52.6 (#79)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena Non-English | 1412 | — |
| LMArena Chinese | 1448 | — |
| LMArena French | 1456 | — |
| LMArena German | 1438 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1412 | — |
| LMArena Spanish | 1437 | — |

## Instruction Following

- Mistral Large 3: 74.1 (#104)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena Instruction Following | 1402 | — |

## Long Context

- Mistral Large 3: 43.1 (#102)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena Longer Query | 1413 | — |

## Writing & Preference

- Mistral Large 3: 60.2 (#100)
- o1-pro: —

| Benchmark | Mistral Large 3 | o1-pro |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1385 | — |
| EQ-Bench Creative Writing | 1412 | — |
| LMArena Multi-Turn | 1429 | — |

## FAQ

### Is Mistral Large 3 better than o1-pro?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.2 on the Noometry Index.

### Which is cheaper, Mistral Large 3 or o1-pro?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; o1-pro lists at $150 and $600.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 200K.

### How many benchmarks do Mistral Large 3 and o1-pro share?

0 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and o1-pro has 3.