# Grok-3 mini vs Mistral Small 3

> Grok-3 mini is the stronger model overall, scoring 41.2 to 31.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-mistral-small-3
- Last updated: 2026-10-12
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Mistral Small 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 42.1 to 16.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 6.7% for Mistral Small 3.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 41.2 | 31.2 |
| Rank | 141 | 278 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.8 (#131)
- Mistral Small 3: 36.5 (#207)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1379 | 1246 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Mistral Small 3: 18.9 (#273)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1233 |
| Epoch Capabilities Index | 140.35 | 127.07 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Chess Puzzles | — | 0% |

## Math

- Grok-3 mini: 42.1 (#85)
- Mistral Small 3: 16.3 (#295)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 6.7% |
| LMArena Math | 1386 | 1240 |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.4 (#81)
- Mistral Small 3: 25.1 (#263)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 76.3% | 47.3% |
| Confabulations | 10.8% | 25.2% |
| LMArena Expert | 1395 | 1202 |
| MMLU-Pro | 79.9% | — |
| GPQA (HELM) | 67.5% | — |

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Mistral Small 3: 37.3 (#236)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1352 | 1198 |
| LMArena Chinese | 1387 | 1204 |
| LMArena French | 1357 | 1203 |
| LMArena German | 1349 | 1211 |
| LMArena Japanese | 1342 | 1111 |
| LMArena Korean | 1335 | 1188 |
| LMArena Russian | 1353 | 1216 |
| LMArena Spanish | 1381 | — |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Mistral Small 3: 63.7 (#229)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1214 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Mistral Small 3: 37.8 (#211)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1372 | 1246 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Mistral Small 3: 32.2 (#280)

| Benchmark | Grok-3 mini | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1370 | 1234 |
| LMArena Creative Writing | 1342 | 1195 |
| LMArena Multi-Turn | 1355 | 1217 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 707 |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Mistral Small 3?

Grok-3 mini is the stronger model overall, scoring 41.2 to 31.2 on the Noometry Index.

### Is Grok-3 mini or Mistral Small 3 better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 36.5 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Mistral Small 3 share?

20 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Mistral Small 3 has 24.