# Mistral Small 3 vs o3-pro

> o3-pro is the stronger model overall, scoring 42.7 to 30.9 on the Noometry Index. Mistral Small 3 costs 609× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-o3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 37.8.
- The biggest single-benchmark swing is Confabulations: 25.2% for Mistral Small 3 and 14.2% for o3-pro.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small 3 | o3-pro |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.9 | 42.7 |
| Rank | 268 | 94 |
| Context | 33K | 200K |
| Input $/M | $0.05 | $20 |
| Output $/M | $0.08 | $80 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small 3: 36.0 (#203)
- o3-pro: 55.1 (#22)

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| BigCodeBench Instruct | 45.3% | — |
| LMArena Coding | 1246 | — |
| BigCodeBench Complete | 50.4% | — |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- o3-pro: 24.1 (#152)

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Epoch Capabilities Index | 127.06 | 147.43 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1233 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |

## Math

- Mistral Small 3: 15.3 (#290)
- o3-pro: —

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1240 | — |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- o3-pro: 29.0 (#234)

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Confabulations | 25.2% | 14.2% |
| GPQA Diamond | 47.3% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1202 | — |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- o3-pro: —

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| LMArena Non-English | 1198 | — |
| LMArena Chinese | 1204 | — |
| LMArena French | 1202 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- o3-pro: —

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1214 | — |

## Long Context

- Mistral Small 3: 37.8 (#206)
- o3-pro: 72.1 (#1)

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1246 | — |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- o3-pro: 57.1 (#128)

| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| LMArena Text | 1234 | — |
| LMArena Creative Writing | 1195 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 707 | — |
| LMArena Multi-Turn | 1217 | — |

## FAQ

### Is Mistral Small 3 better than o3-pro?

o3-pro is the stronger model overall, scoring 42.7 to 30.9 on the Noometry Index. Mistral Small 3 costs 609× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3 or o3-pro?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; o3-pro lists at $20 and $80.

### Is Mistral Small 3 or o3-pro better for coding?

o3-pro scores higher on coding benchmarks: 55.1 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

o3-pro does, with 200K tokens against 33K.

### How many benchmarks do Mistral Small 3 and o3-pro share?

2 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and o3-pro has 12.