# gpt-oss-20b vs Mistral Medium 3.5

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 32.1 on the Noometry Index. gpt-oss-20b costs 83× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Mistral Medium 3.5 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.6 to 35.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for gpt-oss-20b and 41.4% for Mistral Medium 3.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 131K.

## Snapshot

| | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.1 | 39.6 |
| Rank | 249 | 151 |
| Context | 131K | 262K |
| Input $/M | $0.018 | $1.50 |
| Output $/M | $0.09 | $7.50 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1307 | 1461 |
| LMArena WebDev | — | 1263 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Mistral Medium 3.5: —

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 41.4% |
| LMArena Hard Prompts | 1274 | 1436 |
| Epoch Capabilities Index | 137.81 | 141.42 |
| NYT Connections (extended) | — | 12.9% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |

## Math

- gpt-oss-20b: 37.6 (#93)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1317 | 1432 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1258 | 1431 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |

## Multimodal

- gpt-oss-20b: —
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1269 | 1405 |
| LMArena Chinese | 1311 | 1443 |
| LMArena German | 1249 | 1453 |
| LMArena Korean | 1239 | 1387 |
| LMArena Russian | 1279 | 1396 |
| LMArena Spanish | 1267 | 1406 |
| LMArena French | — | 1448 |
| LMArena Japanese | 1245 | — |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1414 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1251 | 1414 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | gpt-oss-20b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1288 | 1421 |
| LMArena Creative Writing | 1201 | 1372 |
| LMArena Multi-Turn | 1268 | 1423 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is gpt-oss-20b better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 32.1 on the Noometry Index. gpt-oss-20b costs 83× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-20b or Mistral Medium 3.5?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is gpt-oss-20b or Mistral Medium 3.5 better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 131K.

### How many benchmarks do gpt-oss-20b and Mistral Medium 3.5 share?

17 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral Medium 3.5 has 22.