# gpt-oss-20b vs Mistral Small 3

> gpt-oss-20b is the stronger model overall, scoring 32.5 to 31.2 on the Noometry Index.

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

## Summary

- They share 20 benchmarks with published results for both. gpt-oss-20b scores higher in 7 categories and Mistral Small 3 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 16.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 6.7% for Mistral Small 3.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.05 / $0.08 for Mistral Small 3.
- gpt-oss-20b accepts more context: 131K tokens versus 33K.

## Snapshot

| | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.5 | 31.2 |
| Rank | 255 | 278 |
| Context | 131K | 33K |
| Input $/M | $0.018 | $0.05 |
| Output $/M | $0.09 | $0.08 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.6 (#192)
- Mistral Small 3: 36.5 (#207)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1306 | 1246 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- Mistral Small 3: —

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- Mistral Small 3: 18.9 (#273)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 4% | 0% |
| LMArena Hard Prompts | 1274 | 1233 |
| Epoch Capabilities Index | 137.82 | 127.07 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |

## Math

- gpt-oss-20b: 39.4 (#103)
- Mistral Small 3: 16.3 (#295)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 6.7% |
| LMArena Math | 1317 | 1240 |
| Omni-MATH | 56.5% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- Mistral Small 3: 25.1 (#263)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 60.8% | 47.3% |
| LMArena Expert | 1258 | 1202 |
| MMLU-Pro | 74% | — |
| Confabulations | — | 25.2% |
| GPQA (HELM) | 59.4% | — |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- Mistral Small 3: 37.3 (#236)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1268 | 1198 |
| LMArena Chinese | 1314 | 1204 |
| LMArena German | 1255 | 1211 |
| LMArena Japanese | 1244 | 1111 |
| LMArena Korean | 1236 | 1188 |
| LMArena Russian | 1278 | 1216 |
| LMArena French | — | 1203 |
| LMArena Spanish | 1267 | — |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- Mistral Small 3: 63.7 (#229)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1214 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- Mistral Small 3: 37.8 (#211)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1250 | 1246 |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- Mistral Small 3: 32.2 (#280)

| Benchmark | gpt-oss-20b | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1287 | 1234 |
| LMArena Creative Writing | 1201 | 1195 |
| EQ-Bench Creative Writing | 666 | 707 |
| LMArena Multi-Turn | 1268 | 1217 |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than Mistral Small 3?

gpt-oss-20b is the stronger model overall, scoring 32.5 to 31.2 on the Noometry Index.

### Which is cheaper, gpt-oss-20b or Mistral Small 3?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mistral Small 3 lists at $0.05 and $0.08.

### Is gpt-oss-20b or Mistral Small 3 better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

gpt-oss-20b does, with 131K tokens against 33K.

### How many benchmarks do gpt-oss-20b and Mistral Small 3 share?

20 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral Small 3 has 24.