# gpt-oss-120b vs Mixtral 8x22B

> gpt-oss-120b is the stronger model overall, scoring 36.0 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-120b-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. gpt-oss-120b scores higher in 7 categories and Mixtral 8x22B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 21.2.
- The biggest single-benchmark swing is Omni-MATH: 68.8% for gpt-oss-120b and 16.3% for Mixtral 8x22B.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- gpt-oss-120b accepts more context: 131K tokens versus 64K.

## Snapshot

| | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.0 | 26.7 |
| Rank | 210 | 330 |
| Context | 131K | 64K |
| Input $/M | $0.037 | $2 |
| Output $/M | $0.17 | $6 |
| Weights | Open | Open |

## Coding

- gpt-oss-120b: 33.2 (#251)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| WeirdML | 48.2% | 3.2% |
| LMArena Coding | 1380 | 1166 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- gpt-oss-120b: 12.1 (#145)
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Cybench | — | 7.5% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |

## Reasoning

- gpt-oss-120b: 19.5 (#236)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1150 |
| DTBench | 76.3% | 55.1% |
| Epoch Capabilities Index | 139.94 | 122 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| ForecastBench | — | 56.3 |

## Math

- gpt-oss-120b: 50.6 (#43)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 68.8% | 16.3% |
| LMArena Math | 1388 | 1184 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| MATH Level 5 | — | 24.2% |

## Knowledge

- gpt-oss-120b: 42.3 (#89)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 75.8% | 34.1% |
| MMLU-Pro | 79.5% | 46% |
| GPQA (HELM) | 68.4% | 33.4% |
| LMArena Expert | 1356 | 1113 |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| MMLU | — | 77.8% |

## Multilingual

- gpt-oss-120b: 48.2 (#142)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1350 | 1128 |
| LMArena Chinese | 1384 | 1116 |
| LMArena French | 1370 | 1165 |
| LMArena German | 1355 | 1141 |
| LMArena Japanese | 1332 | 1037 |
| LMArena Korean | 1283 | 1056 |
| LMArena Russian | 1343 | 1158 |
| LMArena Spanish | 1388 | 1150 |

## Instruction Following

- gpt-oss-120b: 69.5 (#168)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| IFEval | 83.6% | 72.4% |
| LMArena Instruction Following | 1318 | 1147 |

## Long Context

- gpt-oss-120b: 31.4 (#273)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1319 | 1144 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- gpt-oss-120b: 46.7 (#213)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | gpt-oss-120b | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1366 | 1162 |
| LMArena Creative Writing | 1274 | 1141 |
| WildBench | 84.5% | 71.1% |
| LMArena Multi-Turn | 1340 | 1130 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |

## FAQ

### Is gpt-oss-120b better than Mixtral 8x22B?

gpt-oss-120b is the stronger model overall, scoring 36.0 to 26.7 on the Noometry Index.

### Which is cheaper, gpt-oss-120b or Mixtral 8x22B?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is gpt-oss-120b or Mixtral 8x22B better for coding?

gpt-oss-120b scores higher on coding benchmarks: 33.2 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

gpt-oss-120b does, with 131K tokens against 64K.

### How many benchmarks do gpt-oss-120b and Mixtral 8x22B share?

26 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Mixtral 8x22B has 34.