# gpt-oss-20b vs Mistral Small

> gpt-oss-20b and Mistral Small score almost the same on the Noometry Index (32.5 vs 33.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mistral-small
- Last updated: 2026-10-11
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Mistral Small in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 5.8% for Mistral Small.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 262K tokens versus 131K.

## Snapshot

| | gpt-oss-20b | Mistral Small |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.5 | 33.4 |
| Rank | 255 | 243 |
| Context | 131K | 262K |
| Input $/M | $0.018 | $0.15 |
| Output $/M | $0.09 | $0.60 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.6 (#192)
- Mistral Small: 34.0 (#247)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| SciCode | 34.4% | 26.5% |
| LMArena Coding | 1306 | 1362 |
| ALE-Bench | 566.05 | 497.62 |
| WeirdML | 40.9% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- Mistral Small: 28.1 (#93)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- Mistral Small: 19.8 (#250)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 37.8% |
| CritPt | 1.4% | 0% |
| LMArena Hard Prompts | 1274 | 1335 |
| DTBench | 68% | 70.9% |
| LMCA | 14.5% | 20.6% |
| Chess Puzzles | 4% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 137.82 | — |
| LiveBench | — | 44% |

## Math

- gpt-oss-20b: 39.4 (#103)
- Mistral Small: 16.4 (#293)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 5.8% |
| LMArena Math | 1317 | 1341 |
| Omni-MATH | 56.5% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- Mistral Small: 31.0 (#222)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| GPQA Diamond | 60.8% | 47.5% |
| LMArena Expert | 1258 | 1291 |
| MMLU-Pro | 74% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 68.7% |

## Multimodal

- gpt-oss-20b: —
- Mistral Small: 33.5 (#96)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- Mistral Small: 45.5 (#169)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| LMArena Non-English | 1268 | 1315 |
| LMArena Chinese | 1314 | 1340 |
| LMArena German | 1255 | 1340 |
| LMArena Japanese | 1244 | 1275 |
| LMArena Korean | 1236 | 1259 |
| LMArena Russian | 1278 | 1324 |
| LMArena Spanish | 1267 | 1346 |
| LMArena French | — | 1337 |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- Mistral Small: 66.4 (#209)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1236 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- Mistral Small: 40.4 (#156)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1250 | 1327 |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- Mistral Small: 52.5 (#171)

| Benchmark | gpt-oss-20b | Mistral Small |
|---|---|---|
| LMArena Text | 1287 | 1338 |
| LMArena Creative Writing | 1201 | 1305 |
| LMArena Multi-Turn | 1268 | 1344 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LiveBench Language | — | 30.5% |

## FAQ

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

gpt-oss-20b and Mistral Small score almost the same on the Noometry Index (32.5 vs 33.4), so choose on price, context window or the category you care about most.

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

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mistral Small lists at $0.15 and $0.60.

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

gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small does, with 262K tokens against 131K.

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

24 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral Small has 39.