# Mistral Small 3.1 vs Step 3

> Step 3 is the stronger model overall, scoring 39.9 to 31.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-3-1-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Mistral Small 3.1 scores higher in 0 categories and Step 3 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 34.9 to 13.7.

## Snapshot

| | Mistral Small 3.1 | Step 3 |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 31.4 | 39.9 |
| Rank | 263 | 145 |
| Context | 128K | — |
| Input $/M | $0.35 | — |
| Output $/M | $0.56 | — |
| Weights | Open | Open |

## Coding

- Mistral Small 3.1: 37.7 (#175)
- Step 3: 39.5 (#144)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Coding | 1309 | 1367 |

## Reasoning

- Mistral Small 3.1: 18.9 (#249)
- Step 3: 27.6 (#102)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 1% | — |
| Epoch Capabilities Index | 127.48 | — |

## Math

- Mistral Small 3.1: 13.7 (#295)
- Step 3: 34.9 (#148)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Math | 1261 | 1366 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| Omni-MATH | 24.8% | — |

## Knowledge

- Mistral Small 3.1: 22.6 (#266)
- Step 3: 36.2 (#161)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Expert | 1258 | 1333 |
| GPQA Diamond | 41.9% | — |
| MMLU-Pro | 61% | — |
| GPQA (HELM) | 39.2% | — |

## Multimodal

- Mistral Small 3.1: 32.6 (#93)
- Step 3: 34.9 (#81)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Vision | 1136 | 1176 |

## Multilingual

- Mistral Small 3.1: 41.4 (#204)
- Step 3: 46.5 (#154)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1255 | 1327 |
| LMArena Chinese | 1254 | 1396 |
| LMArena German | 1266 | 1371 |
| LMArena Korean | 1206 | 1271 |
| LMArena Russian | 1263 | 1331 |
| LMArena Spanish | 1283 | 1372 |
| LMArena French | 1270 | — |
| LMArena Japanese | 1210 | — |

## Instruction Following

- Mistral Small 3.1: 63.8 (#225)
- Step 3: 70.6 (#159)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1264 | 1332 |
| IFEval | 75% | — |

## Long Context

- Mistral Small 3.1: 39.5 (#172)
- Step 3: 40.3 (#152)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1300 | 1326 |

## Writing & Preference

- Mistral Small 3.1: 37.2 (#254)
- Step 3: 54.5 (#146)

| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Text | 1278 | 1351 |
| LMArena Creative Writing | 1253 | 1322 |
| LMArena Multi-Turn | 1270 | 1340 |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |

## FAQ

### Is Mistral Small 3.1 better than Step 3?

Step 3 is the stronger model overall, scoring 39.9 to 31.4 on the Noometry Index.

### Is Mistral Small 3.1 or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 39.5 versus 37.7 in the Noometry coding category.

### How many benchmarks do Mistral Small 3.1 and Step 3 share?

16 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Step 3 has 17.