WizardLM-2 8x22B: benchmark results
Microsoft's Mixtral-8x22B finetune briefly pulled days after its April 2024 release over missing toxicity testing, surviving via community mirrors. Provider: Microsoft. Released 2024-04-15. Access: Open.
Unified ELO 1511 ± 1, rank #644 of 1392 rated models, from 52 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - GPQA | 17.56 | Score | 95.3 |
| LogicKor - Reasoning | 8.5 | Score (0-10) | 89.1 |
| Open Chinese LLM - GSM8K | 64.82 | Accuracy (%) | 89 |
| Open LLM Leaderboard - BBH | 48.58 | Score | 88.9 |
| LogicKor - Single-Turn | 8.52 | Score (0-10) | 87.2 |
| LogicKor - Writing | 9.35 | Score (0-10) | 85.7 |
| Open LLM Leaderboard - MMLU-Pro | 39.96 | Score | 84.9 |
| LogicKor - Coding | 9.28 | Score (0-10) | 84.5 |
| LogicKor | 8.13 | Score (0-10) | 83.2 |
| Open PL LLM - Generative | 66.42 | Average Generative Score (%) | 82.2 |
| Open PL LLM Leaderboard | 62.35 | Average Score (%) | 80.4 |
| LogicKor - Multi-Turn | 7.73 | Score (0-10) | 80 |
Interactive version: theaggregate.ai/model?slug=wizardlm-2-8x22b · How It Works · Data refreshed daily, snapshot 2026-09-05.