# GPT-4.5 vs Mistral

> GPT-4.5 is the stronger model overall, scoring 36.9 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-mistral
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and Mistral in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-4.5 leads 72.8 to 52.9.

## Snapshot

| | GPT-4.5 | Mistral |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.9 | 29.4 |
| Rank | 200 | 297 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.5: 41.8 (#102)
- Mistral: 33.2 (#249)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Coding | 1397 | 1162 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |

## Agentic & Tool Use

- GPT-4.5: 27.6 (#92)
- Mistral: —

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

## Reasoning

- GPT-4.5: 14.1 (#320)
- Mistral: 21.3 (#199)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1149 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 31.0 (#200)
- Mistral: 20.5 (#275)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Math | 1412 | 1180 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | — | 7.2% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.4 (#205)
- Mistral: 16.3 (#283)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Expert | 1394 | 1125 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | — | 27.7% |
| Confabulations | 13.6% | — |
| GPQA (HELM) | — | 30.3% |

## Multimodal

- GPT-4.5: 37.0 (#68)
- Mistral: —

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

## Multilingual

- GPT-4.5: 52.7 (#78)
- Mistral: 33.0 (#249)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Non-English | 1413 | 1129 |
| LMArena Chinese | 1421 | 1109 |
| LMArena French | 1417 | 1179 |
| LMArena German | 1457 | 1155 |
| LMArena Japanese | 1416 | 1012 |
| LMArena Korean | 1392 | 1032 |
| LMArena Russian | 1419 | 1168 |
| LMArena Spanish | — | 1143 |

## Instruction Following

- GPT-4.5: 72.8 (#129)
- Mistral: 52.9 (#283)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Instruction Following | 1404 | 1152 |
| LiveBench Instruction Following | 72.3% | — |
| IFEval | — | 56.8% |

## Long Context

- GPT-4.5: 40.4 (#150)
- Mistral: 35.0 (#240)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Longer Query | 1406 | 1154 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 57.1 (#129)
- Mistral: 37.2 (#255)

| Benchmark | GPT-4.5 | Mistral |
|---|---|---|
| LMArena Text | 1417 | 1165 |
| LMArena Creative Writing | 1394 | 1158 |
| LMArena Multi-Turn | 1444 | 1147 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| WildBench | — | 66% |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Mistral?

GPT-4.5 is the stronger model overall, scoring 36.9 to 29.4 on the Noometry Index.

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

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 33.2 in the Noometry coding category.

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

16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Mistral has 22.