Mixtral 8x22B Instruct v0.1 — Benchmarks
Benchmark scores for Mixtral 8x22B Instruct v0.1 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #68 of 78 open modelscomposite 24.4/100 across 5 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| WeirdML | 3.2% | #45 / 46 | #160 / 161 |
Instruction Following
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LMArena Text | 1229.3 | #130 / 182 | #308 / 391 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 56.3% | #63 / 144 | #150 / 257 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MATH Level 5 | 24.2% | #27 / 39 | #84 / 107 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| DTBench | 55.1% | #53 / 67 | #177 / 210 |
| GPQA Diamond | 34.1% | #74 / 94 | #257 / 289 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.