# Mistral Medium 3.5 vs o3-mini

> Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 36.7 on the Noometry Index. o3-mini costs 1.6× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-medium-3-5-vs-o3-mini
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 6 categories and o3-mini in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 39.1 to 28.1.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 200K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 40.2 | 36.7 |
| Rank | 152 | 212 |
| Context | 262K | 200K |
| Input $/M | $1.50 | $1.10 |
| Output $/M | $7.50 | $4.40 |
| Weights | Open | Proprietary |

## Coding

- Mistral Medium 3.5: 36.0 (#213)
- o3-mini: 40.8 (#132)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Coding | 1461 | 1378 |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1264 | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |

## Agentic & Tool Use

- Mistral Medium 3.5: —
- o3-mini: 29.6 (#84)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |

## Reasoning

- Mistral Medium 3.5: 17.3 (#295)
- o3-mini: 16.3 (#305)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1366 |
| Epoch Capabilities Index | 141.35 | 140.34 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |

## Math

- Mistral Medium 3.5: 39.1 (#113)
- o3-mini: 28.1 (#244)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Math | 1431 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Mistral Medium 3.5: 40.0 (#126)
- o3-mini: 38.3 (#146)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Expert | 1432 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |

## Multimodal

- Mistral Medium 3.5: 38.3 (#65)
- o3-mini: —

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Vision | 1223 | — |

## Multilingual

- Mistral Medium 3.5: 51.9 (#100)
- o3-mini: 45.7 (#164)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Non-English | 1404 | 1319 |
| LMArena Chinese | 1442 | 1379 |
| LMArena French | 1448 | 1334 |
| LMArena German | 1451 | 1303 |
| LMArena Korean | 1385 | 1314 |
| LMArena Russian | 1395 | 1304 |
| LMArena Spanish | 1409 | 1321 |
| LMArena Japanese | — | 1286 |

## Instruction Following

- Mistral Medium 3.5: 74.6 (#90)
- o3-mini: 75.1 (#72)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1415 | 1337 |
| LiveBench Instruction Following | — | 84.4% |

## Long Context

- Mistral Medium 3.5: 43.2 (#103)
- o3-mini: 33.8 (#256)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1415 | 1343 |
| Fiction.LiveBench | — | 50% |

## Writing & Preference

- Mistral Medium 3.5: 58.5 (#117)
- o3-mini: 50.3 (#182)

| Benchmark | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| LMArena Text | 1421 | 1337 |
| LMArena Creative Writing | 1374 | 1286 |
| LMArena Multi-Turn | 1423 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench 4 | 993 | — |
| LiveBench Language | — | 50.7% |

## FAQ

### Is Mistral Medium 3.5 better than o3-mini?

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 36.7 on the Noometry Index. o3-mini costs 1.6× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

### Which is cheaper, Mistral Medium 3.5 or o3-mini?

o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or o3-mini better for coding?

o3-mini scores higher on coding benchmarks: 40.8 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 200K.

### How many benchmarks do Mistral Medium 3.5 and o3-mini share?

17 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and o3-mini has 51.