# gpt-oss-20b vs Mistral Small 3.2

> gpt-oss-20b is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mistral-small-3-2
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Mistral Small 3.2 in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 37.6 to 24.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 30.3% for Mistral Small 3.2.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.0938 / $0.25 for Mistral Small 3.2.
- Mistral Small 3.2 accepts more context: 256K tokens versus 131K.

## Snapshot

| | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.1 | 30.8 |
| Rank | 249 | 271 |
| Context | 131K | 256K |
| Input $/M | $0.018 | $0.0938 |
| Output $/M | $0.09 | $0.25 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Mistral Small 3.2: —

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LMArena Coding | 1307 | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Mistral Small 3.2: —

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Mistral Small 3.2: 17.5 (#282)

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 40.4% |
| Chess Puzzles | 4% | 1% |
| Epoch Capabilities Index | 137.81 | 131.73 |
| CritPt | 1.4% | — |
| LMArena Hard Prompts | 1274 | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |

## Math

- gpt-oss-20b: 37.6 (#93)
- Mistral Small 3.2: 24.9 (#251)

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 30.3% |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Mistral Small 3.2: 26.8 (#249)

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| GPQA Diamond | 60.8% | 49.1% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Mistral Small 3.2: —

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1311 | — |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Russian | 1279 | — |
| LMArena Spanish | 1267 | — |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Mistral Small 3.2: —

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Mistral Small 3.2: —

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| LMArena Longer Query | 1251 | — |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Mistral Small 3.2: 45.1 (#219)

| Benchmark | gpt-oss-20b | Mistral Small 3.2 |
|---|---|---|
| EQ-Bench Creative Writing | 666 | 1255 |
| LMArena Text | 1288 | — |
| LMArena Creative Writing | 1201 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |

## FAQ

### Is gpt-oss-20b better than Mistral Small 3.2?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.

### Which is cheaper, gpt-oss-20b or Mistral Small 3.2?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mistral Small 3.2 lists at $0.0938 and $0.25.

### Which has the bigger context window?

Mistral Small 3.2 does, with 256K tokens against 131K.

### How many benchmarks do gpt-oss-20b and Mistral Small 3.2 share?

6 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral Small 3.2 has 6.