# GPT-4.5 vs Mistral Small 3.1

> GPT-4.5 is the stronger model overall, scoring 36.9 to 31.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-mistral-small-3-1
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and Mistral Small 3.1 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 37.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.9 | 31.4 |
| Rank | 200 | 263 |
| Context | — | 128K |
| Input $/M | — | $0.35 |
| Output $/M | — | $0.56 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.5: 41.8 (#102)
- Mistral Small 3.1: 37.7 (#175)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1397 | 1309 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |

## Agentic & Tool Use

- GPT-4.5: 27.6 (#92)
- Mistral Small 3.1: —

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| Cybench | 17.5% | — |

## Reasoning

- GPT-4.5: 14.1 (#320)
- Mistral Small 3.1: 18.9 (#249)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1278 |
| Epoch Capabilities Index | 136.74 | 127.48 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| Chess Puzzles | — | 1% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 31.0 (#200)
- Mistral Small 3.1: 13.7 (#295)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 3.9% |
| LMArena Math | 1412 | 1261 |
| Omni-MATH | — | 24.8% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.4 (#205)
- Mistral Small 3.1: 22.6 (#266)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 68.7% | 41.9% |
| LMArena Expert | 1394 | 1258 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | — | 61% |
| Confabulations | 13.6% | — |
| GPQA (HELM) | — | 39.2% |

## Multimodal

- GPT-4.5: 37.0 (#68)
- Mistral Small 3.1: 32.6 (#93)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1195 | 1136 |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.7 (#78)
- Mistral Small 3.1: 41.4 (#204)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1413 | 1255 |
| LMArena Chinese | 1421 | 1254 |
| LMArena French | 1417 | 1270 |
| LMArena German | 1457 | 1266 |
| LMArena Japanese | 1416 | 1210 |
| LMArena Korean | 1392 | 1206 |
| LMArena Russian | 1419 | 1263 |
| LMArena Spanish | — | 1283 |

## Instruction Following

- GPT-4.5: 72.8 (#129)
- Mistral Small 3.1: 63.8 (#225)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1264 |
| LiveBench Instruction Following | 72.3% | — |
| IFEval | — | 75% |

## Long Context

- GPT-4.5: 40.4 (#150)
- Mistral Small 3.1: 39.5 (#172)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1406 | 1300 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 57.1 (#129)
- Mistral Small 3.1: 37.2 (#254)

| Benchmark | GPT-4.5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1417 | 1278 |
| LMArena Creative Writing | 1394 | 1253 |
| EQ-Bench Creative Writing | 1258 | 761 |
| LMArena Multi-Turn | 1444 | 1270 |
| Short-Story Creative Writing | 75.6% | — |
| WildBench | — | 78.8% |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Mistral Small 3.1?

GPT-4.5 is the stronger model overall, scoring 36.9 to 31.4 on the Noometry Index.

### Is GPT-4.5 or Mistral Small 3.1 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 37.7 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and Mistral Small 3.1 share?

21 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Mistral Small 3.1 has 28.