# gpt-oss-20b vs Mistral

> gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mistral
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. gpt-oss-20b scores higher in 6 categories and Mistral in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 16.3.
- The biggest single-benchmark swing is Omni-MATH: 56.5% for gpt-oss-20b and 7.2% for Mistral.
- gpt-oss-20b has downloadable open weights; the other is API-only.

## Snapshot

| | gpt-oss-20b | Mistral |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.1 | 29.4 |
| Rank | 249 | 297 |
| Context | 131K | — |
| Input $/M | $0.018 | — |
| Output $/M | $0.09 | — |
| Weights | Open | Proprietary |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Mistral: 33.2 (#249)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| LMArena Coding | 1307 | 1162 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Mistral: —

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Mistral: 21.3 (#199)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1149 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |

## Math

- gpt-oss-20b: 37.6 (#93)
- Mistral: 20.5 (#275)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| Omni-MATH | 56.5% | 7.2% |
| LMArena Math | 1317 | 1180 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Mistral: 16.3 (#283)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| MMLU-Pro | 74% | 27.7% |
| GPQA (HELM) | 59.4% | 30.3% |
| LMArena Expert | 1258 | 1125 |
| GPQA Diamond | 60.8% | — |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Mistral: 33.0 (#249)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| LMArena Non-English | 1269 | 1129 |
| LMArena Chinese | 1311 | 1109 |
| LMArena German | 1249 | 1155 |
| LMArena Japanese | 1245 | 1012 |
| LMArena Korean | 1239 | 1032 |
| LMArena Russian | 1279 | 1168 |
| LMArena Spanish | 1267 | 1143 |
| LMArena French | — | 1179 |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Mistral: 52.9 (#283)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| IFEval | 73.2% | 56.8% |
| LMArena Instruction Following | 1236 | 1152 |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Mistral: 35.0 (#240)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| LMArena Longer Query | 1251 | 1154 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Mistral: 37.2 (#255)

| Benchmark | gpt-oss-20b | Mistral |
|---|---|---|
| LMArena Text | 1288 | 1165 |
| LMArena Creative Writing | 1201 | 1158 |
| WildBench | 73.7% | 66% |
| LMArena Multi-Turn | 1268 | 1147 |
| EQ-Bench Creative Writing | 666 | — |

## FAQ

### Is gpt-oss-20b better than Mistral?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.4 on the Noometry Index.

### Is gpt-oss-20b or Mistral better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 33.2 in the Noometry coding category.

### How many benchmarks do gpt-oss-20b and Mistral share?

21 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral has 22.