# Mistral Large vs o3

> o3 is the stronger model overall, scoring 47.5 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-vs-o3
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Mistral Large scores higher in 0 categories and o3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o3 leads 50.2 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 84.4% for o3.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Large | o3 |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 31.9 | 47.5 |
| Rank | 263 | 61 |
| Context | 131K | 200K |
| Input $/M | $2 | $2 |
| Output $/M | $6 | $8 |
| Weights | Open | Proprietary |

## Coding

- Mistral Large: 34.3 (#240)
- o3: 46.8 (#64)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| LMArena Coding | 1277 | 1408 |
| ALE-Bench | 264.7 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| SciCode | 36.2% | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| CadEval | — | 74% |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |

## Agentic & Tool Use

- Mistral Large: 28.6 (#89)
- o3: 34.5 (#44)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |

## Reasoning

- Mistral Large: 15.8 (#310)
- o3: 32.0 (#78)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| SimpleBench | 22.5% | 53.1% |
| CritPt | 0% | 1.4% |
| LMArena Hard Prompts | 1257 | 1402 |
| DTBench | 65.1% | 84.8% |
| LMCA | 16.7% | 39.7% |
| Epoch Capabilities Index | 128.52 | 146.86 |
| ForecastBench | 57.1 | 62.5 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 29% |
| LiveBench Data Analysis | 50.1% | — |
| LiveBench | 48.4% | — |

## Math

- Mistral Large: 18.2 (#291)
- o3: 50.2 (#58)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 84.4% |
| Omni-MATH | 28.1% | 71.4% |
| LMArena Math | 1262 | 1426 |
| MATH Level 5 | 50.3% | 97.8% |
| FrontierMath (Feb 2025 set) | 0.3% | 18.7% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| LiveBench Math | 42.5% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Mistral Large: 30.1 (#230)
- o3: 54.6 (#52)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| GPQA Diamond | 51.3% | 81.8% |
| MMLU-Pro | 59.9% | 85.9% |
| Confabulations | 21.4% | 14.4% |
| GPQA (HELM) | 43.5% | 75.3% |
| LMArena Expert | 1232 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| Vectara Hallucination Rate | 4.5% | — |
| MMLU | 80% | — |

## Multimodal

- Mistral Large: —
- o3: 41.4 (#36)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |

## Multilingual

- Mistral Large: 40.0 (#219)
- o3: 51.7 (#105)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| LMArena Non-English | 1237 | 1401 |
| LMArena Chinese | 1240 | 1437 |
| LMArena French | 1325 | 1430 |
| LMArena German | 1254 | 1420 |
| LMArena Japanese | 1188 | 1403 |
| LMArena Korean | 1202 | 1370 |
| LMArena Russian | 1257 | 1406 |
| LMArena Spanish | 1268 | 1395 |

## Instruction Following

- Mistral Large: 67.9 (#191)
- o3: 72.8 (#127)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| IFEval | 87.7% | 86.9% |
| LMArena Instruction Following | 1249 | 1368 |
| LiveBench Instruction Following | 67.9% | — |

## Long Context

- Mistral Large: 38.3 (#199)
- o3: 53.3 (#6)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| LMArena Longer Query | 1261 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- Mistral Large: 40.7 (#242)
- o3: 63.5 (#64)

| Benchmark | Mistral Large | o3 |
|---|---|---|
| LMArena Text | 1266 | 1410 |
| LMArena Creative Writing | 1243 | 1359 |
| Short-Story Creative Writing | 69% | 83.9% |
| EQ-Bench Creative Writing | 985 | 1676 |
| WildBench | 80.1% | 86.1% |
| LMArena Multi-Turn | 1260 | 1405 |
| LiveBench Language | 39.4% | — |

## FAQ

### Is Mistral Large better than o3?

o3 is the stronger model overall, scoring 47.5 to 31.9 on the Noometry Index.

### Which is cheaper, Mistral Large or o3?

Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; o3 lists at $2 and $8.

### Is Mistral Large or o3 better for coding?

o3 scores higher on coding benchmarks: 46.8 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

o3 does, with 200K tokens against 131K.

### How many benchmarks do Mistral Large and o3 share?

37 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and o3 has 63.