# Mistral Small 3.1 vs o1

> o1 is the stronger model overall, scoring 40.9 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 65× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-1-vs-o1
- Last updated: 2026-10-11
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Mistral Small 3.1 scores higher in 0 categories and o1 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o1 leads 36.1 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 3.9% for Mistral Small 3.1 and 73.3% for o1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $15 / $60 for o1.
- o1 accepts more context: 200K tokens versus 128K.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small 3.1 | o1 |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 31.7 | 40.9 |
| Rank | 269 | 143 |
| Context | 128K | 200K |
| Input $/M | $0.35 | $15 |
| Output $/M | $0.56 | $60 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small 3.1: 38.3 (#179)
- o1: 46.1 (#70)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| LMArena Coding | 1309 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |

## Agentic & Tool Use

- Mistral Small 3.1: —
- o1: 24.6 (#117)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |

## Reasoning

- Mistral Small 3.1: 19.7 (#254)
- o1: 27.9 (#111)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| Chess Puzzles | 1% | 15% |
| LMArena Hard Prompts | 1278 | 1371 |
| Epoch Capabilities Index | 127.48 | 141.91 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |

## Math

- Mistral Small 3.1: 14.7 (#301)
- o1: 36.1 (#175)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.9% | 73.3% |
| LMArena Math | 1262 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 24.8% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |

## Knowledge

- Mistral Small 3.1: 22.6 (#271)
- o1: 41.5 (#110)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| GPQA Diamond | 41.9% | 76.8% |
| LMArena Expert | 1257 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 61% | — |
| Confabulations | — | 11.7% |
| GPQA (HELM) | 39.2% | — |

## Multimodal

- Mistral Small 3.1: 33.2 (#99)
- o1: 34.2 (#93)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| LMArena Vision | 1136 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- Mistral Small 3.1: 41.2 (#209)
- o1: 48.6 (#142)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| LMArena Non-English | 1255 | 1358 |
| LMArena Chinese | 1253 | 1394 |
| LMArena French | 1273 | 1344 |
| LMArena German | 1266 | 1337 |
| LMArena Japanese | 1208 | 1346 |
| LMArena Korean | 1206 | 1396 |
| LMArena Russian | 1263 | 1356 |
| LMArena Spanish | 1283 | 1345 |

## Instruction Following

- Mistral Small 3.1: 63.6 (#230)
- o1: 74.8 (#86)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| LMArena Instruction Following | 1264 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 75% | — |

## Long Context

- Mistral Small 3.1: 39.5 (#178)
- o1: 50.3 (#9)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| LMArena Longer Query | 1299 | 1378 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Mistral Small 3.1: 37.0 (#259)
- o1: 55.6 (#144)

| Benchmark | Mistral Small 3.1 | o1 |
|---|---|---|
| LMArena Text | 1277 | 1366 |
| LMArena Creative Writing | 1253 | 1348 |
| LMArena Multi-Turn | 1270 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
| LiveBench Language | — | 65.4% |

## FAQ

### Is Mistral Small 3.1 better than o1?

o1 is the stronger model overall, scoring 40.9 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 65× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3.1 or o1?

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; o1 lists at $15 and $60.

### Is Mistral Small 3.1 or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 38.3 in the Noometry coding category.

### Which has the bigger context window?

o1 does, with 200K tokens against 128K.

### How many benchmarks do Mistral Small 3.1 and o1 share?

22 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and o1 has 52.