dolphin-2.9.1-mixtral-1x22B: benchmark results
Provider: Cognitive Computations. Released 2024-05-22. Access: Open.
Unified ELO 1296 ± 1, rank #1351 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - TruthfulQA MC | 52.87 | Accuracy (%) | 42.9 |
| Open Chinese LLM - GSM8K | 9.4 | Accuracy (%) | 8.5 |
| Open Chinese LLM - ARC Challenge | 37.12 | Accuracy (%) | 4.7 |
| Open Chinese LLM Leaderboard | 34.95 | Average Score (%) | 3.6 |
| Open Korean LLM Leaderboard | 28.95 | Average Score (%) | 3.3 |
| Open Chinese LLM - C-Eval Semantic | 31.39 | Accuracy (%) | 3 |
| Open Chinese LLM - CMMLU | 30.77 | Accuracy (%) | 2.7 |
| Open Chinese LLM - HellaSwag | 31.97 | Accuracy (%) | 2.1 |
| Open Chinese LLM - WinoGrande | 51.14 | Accuracy (%) | 2.1 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-9-1-mixtral-1x22b · How It Works · Data refreshed daily, snapshot 2026-09-05.