# gpt-oss-20b vs Ministral 3B

> gpt-oss-20b is the stronger model overall, scoring 32.5 to 26.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-ministral-3b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Ministral 3B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 10.4.
- The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 25.3% for Ministral 3B.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.10 / $0.10 for Ministral 3B.

## Snapshot

| | gpt-oss-20b | Ministral 3B |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.5 | 26.2 |
| Rank | 255 | 338 |
| Context | 131K | 131K |
| Input $/M | $0.018 | $0.10 |
| Output $/M | $0.09 | $0.10 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.6 (#192)
- Ministral 3B: —

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LMArena Coding | 1306 | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- Ministral 3B: —

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- Ministral 3B: 18.4 (#282)

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| DTBench | 68% | 51.7% |
| LMCA | 14.5% | 5.5% |
| Epoch Capabilities Index | 137.82 | 118.1 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1274 | — |

## Math

- gpt-oss-20b: 39.4 (#103)
- Ministral 3B: 26.6 (#258)

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
| MATH Level 5 | — | 14.4% |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- Ministral 3B: 10.4 (#302)

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| GPQA Diamond | 60.8% | 25.3% |
| MMLU-Pro | 74% | — |
| Vectara Hallucination Rate | — | 7.3% |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- Ministral 3B: —

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1314 | — |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Russian | 1278 | — |
| LMArena Spanish | 1267 | — |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- Ministral 3B: —

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- Ministral 3B: —

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1250 | — |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- Ministral 3B: —

| Benchmark | gpt-oss-20b | Ministral 3B |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |

## FAQ

### Is gpt-oss-20b better than Ministral 3B?

gpt-oss-20b is the stronger model overall, scoring 32.5 to 26.2 on the Noometry Index.

### Which is cheaper, gpt-oss-20b or Ministral 3B?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Ministral 3B lists at $0.10 and $0.10.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do gpt-oss-20b and Ministral 3B share?

4 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Ministral 3B has 6.