# GPT-4.5 vs Mistral Small

> GPT-4.5 is the stronger model overall, scoring 37.2 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-mistral-small
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and Mistral Small in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-4.5 leads 32.6 to 16.4.
- The biggest single-benchmark swing is LiveBench Coding: 75.2% for GPT-4.5 and 36.2% for Mistral Small.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.5 | Mistral Small |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 37.2 | 33.4 |
| Rank | 208 | 243 |
| Context | — | 262K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.5: 42.2 (#109)
- Mistral Small: 34.0 (#247)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LiveBench Coding | 75.2% | 36.2% |
| LMArena Coding | 1396 | 1362 |
| Aider Polyglot | 44.9% | — |
| SciCode | — | 26.5% |
| WeirdML | 39.4% | — |
| BigCodeBench Instruct | — | 36.1% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- GPT-4.5: 27.9 (#97)
- Mistral Small: 28.1 (#93)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| Cybench | 17.5% | — |

## Reasoning

- GPT-4.5: 13.9 (#330)
- Mistral Small: 19.8 (#250)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 71.1% | 44.8% |
| LMArena Hard Prompts | 1403 | 1335 |
| LiveBench Data Analysis | 64.3% | 53.7% |
| LiveBench | 69% | 44% |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 37.8% |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 0% |
| EnigmaEval | 3.2% | — |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |

## Math

- GPT-4.5: 32.6 (#211)
- Mistral Small: 16.4 (#293)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 5.8% |
| LiveBench Math | 69.3% | 39.9% |
| LMArena Math | 1412 | 1341 |
| MATH Level 5 | 78.6% | 46.8% |

## Knowledge

- GPT-4.5: 32.5 (#211)
- Mistral Small: 31.0 (#222)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| GPQA Diamond | 68.7% | 47.5% |
| LMArena Expert | 1394 | 1291 |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- GPT-4.5: 37.6 (#71)
- Mistral Small: 33.5 (#96)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LMArena Vision | 1195 | 1142 |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.5 (#83)
- Mistral Small: 45.5 (#169)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1413 | 1315 |
| LMArena Chinese | 1421 | 1340 |
| LMArena French | 1418 | 1337 |
| LMArena German | 1457 | 1340 |
| LMArena Japanese | 1416 | 1275 |
| LMArena Korean | 1392 | 1259 |
| LMArena Russian | 1419 | 1324 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- GPT-4.5: 72.6 (#134)
- Mistral Small: 66.4 (#209)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 72.3% | 63.7% |
| LMArena Instruction Following | 1404 | 1310 |

## Long Context

- GPT-4.5: 40.4 (#155)
- Mistral Small: 40.4 (#156)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1406 | 1327 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 56.9 (#134)
- Mistral Small: 52.5 (#171)

| Benchmark | GPT-4.5 | Mistral Small |
|---|---|---|
| LMArena Text | 1417 | 1338 |
| LMArena Creative Writing | 1394 | 1305 |
| LMArena Multi-Turn | 1444 | 1344 |
| LiveBench Language | 61.5% | 30.5% |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |

## FAQ

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

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.4 on the Noometry Index.

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

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 34.0 in the Noometry coding category.

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

27 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Mistral Small has 39.