# Mistral Small vs o3

> o3 is the stronger model overall, scoring 47.5 to 33.4 on the Noometry Index. Mistral Small costs 13× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-vs-o3
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Mistral Small scores higher in 0 categories and o3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where o3 leads 50.2 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 84.4% for o3.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $8 for o3.
- Mistral Small accepts more context: 262K tokens versus 200K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small | o3 |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 33.4 | 47.5 |
| Rank | 243 | 61 |
| Context | 262K | 200K |
| Input $/M | $0.15 | $2 |
| Output $/M | $0.60 | $8 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small: 34.0 (#247)
- o3: 46.8 (#64)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| LMArena Coding | 1362 | 1408 |
| ALE-Bench | 497.62 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| SciCode | 26.5% | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| CadEval | — | 74% |

## Agentic & Tool Use

- Mistral Small: 28.1 (#93)
- o3: 34.5 (#44)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |

## Reasoning

- Mistral Small: 19.8 (#250)
- o3: 32.0 (#78)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 67.6% |
| CritPt | 0% | 1.4% |
| LMArena Hard Prompts | 1335 | 1402 |
| DTBench | 70.9% | 84.8% |
| LMCA | 20.6% | 39.7% |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| ARC-AGI-1 | — | 60.8% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 29% |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
| LiveBench | 44% | — |

## Math

- Mistral Small: 16.4 (#293)
- o3: 50.2 (#58)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 84.4% |
| LMArena Math | 1341 | 1426 |
| MATH Level 5 | 46.8% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| Omni-MATH | — | 71.4% |
| LiveBench Math | 39.9% | — |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Mistral Small: 31.0 (#222)
- o3: 54.6 (#52)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| GPQA Diamond | 47.5% | 81.8% |
| LMArena Expert | 1291 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | — | 75.3% |
| MMLU | 68.7% | — |

## Multimodal

- Mistral Small: 33.5 (#96)
- o3: 41.4 (#36)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| LMArena Vision | 1142 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |

## Multilingual

- Mistral Small: 45.5 (#169)
- o3: 51.7 (#105)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| LMArena Non-English | 1315 | 1401 |
| LMArena Chinese | 1340 | 1437 |
| LMArena French | 1337 | 1430 |
| LMArena German | 1340 | 1420 |
| LMArena Japanese | 1275 | 1403 |
| LMArena Korean | 1259 | 1370 |
| LMArena Russian | 1324 | 1406 |
| LMArena Spanish | 1346 | 1395 |

## Instruction Following

- Mistral Small: 66.4 (#209)
- o3: 72.8 (#127)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| LMArena Instruction Following | 1310 | 1368 |
| LiveBench Instruction Following | 63.7% | — |
| IFEval | — | 86.9% |

## Long Context

- Mistral Small: 40.4 (#156)
- o3: 53.3 (#6)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| LMArena Longer Query | 1327 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- Mistral Small: 52.5 (#171)
- o3: 63.5 (#64)

| Benchmark | Mistral Small | o3 |
|---|---|---|
| LMArena Text | 1338 | 1410 |
| LMArena Creative Writing | 1305 | 1359 |
| LMArena Multi-Turn | 1344 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
| LiveBench Language | 30.5% | — |

## FAQ

### Is Mistral Small better than o3?

o3 is the stronger model overall, scoring 47.5 to 33.4 on the Noometry Index. Mistral Small costs 13× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.

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

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; o3 lists at $2 and $8.

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

o3 scores higher on coding benchmarks: 46.8 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small does, with 262K tokens against 200K.

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

27 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and o3 has 63.