# gpt-oss-20b vs Mixtral 8x7B

> gpt-oss-20b is the stronger model overall, scoring 32.1 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-mixtral-8x7b
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. gpt-oss-20b scores higher in 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 11.0.
- The biggest single-benchmark swing is Omni-MATH: 56.5% for gpt-oss-20b and 10.5% for Mixtral 8x7B.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- gpt-oss-20b accepts more context: 131K tokens versus 32K.

## Snapshot

| | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.1 | 26.8 |
| Rank | 249 | 328 |
| Context | 131K | 32K |
| Input $/M | $0.018 | $0.70 |
| Output $/M | $0.09 | $0.70 |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Mixtral 8x7B: 32.2 (#265)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1307 | 1127 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Mixtral 8x7B: —

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Mixtral 8x7B: 17.4 (#283)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1115 |
| DTBench | 68% | 49.6% |
| Epoch Capabilities Index | 137.81 | 118.38 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LMCA | 14.5% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |

## Math

- gpt-oss-20b: 37.6 (#93)
- Mixtral 8x7B: 17.2 (#284)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 56.5% | 10.5% |
| LMArena Math | 1317 | 1147 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Mixtral 8x7B: 11.0 (#296)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 60.8% | 30.6% |
| MMLU-Pro | 74% | 33.5% |
| GPQA (HELM) | 59.4% | 29.6% |
| LMArena Expert | 1258 | 1088 |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Mixtral 8x7B: 29.8 (#261)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1269 | 1077 |
| LMArena Chinese | 1311 | 1055 |
| LMArena German | 1249 | 1114 |
| LMArena Japanese | 1245 | 931 |
| LMArena Korean | 1239 | 968 |
| LMArena Russian | 1279 | 1090 |
| LMArena Spanish | 1267 | 1110 |
| LMArena French | — | 1165 |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Mixtral 8x7B: 51.2 (#292)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| IFEval | 73.2% | 57.5% |
| LMArena Instruction Following | 1236 | 1110 |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Mixtral 8x7B: 33.4 (#255)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1251 | 1103 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Mixtral 8x7B: 34.4 (#265)

| Benchmark | gpt-oss-20b | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1288 | 1132 |
| LMArena Creative Writing | 1201 | 1109 |
| WildBench | 73.7% | 67.3% |
| LMArena Multi-Turn | 1268 | 1115 |
| EQ-Bench Creative Writing | 666 | — |

## FAQ

### Is gpt-oss-20b better than Mixtral 8x7B?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 26.8 on the Noometry Index.

### Which is cheaper, gpt-oss-20b or Mixtral 8x7B?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

### Is gpt-oss-20b or Mixtral 8x7B better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 32.2 in the Noometry coding category.

### Which has the bigger context window?

gpt-oss-20b does, with 131K tokens against 32K.

### How many benchmarks do gpt-oss-20b and Mixtral 8x7B share?

24 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mixtral 8x7B has 38.