openchat_v2: benchmark results
Provider: OpenChat. Access: Open.
Aggregate Rating 1318 ± 14, rank #8368 of 10916 rated models, from 70 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Human Sexuality | 64.89 | Accuracy (%) | 81.2 |
| MMLU-by-task - Professional Medicine | 55.51 | Accuracy (%) | 80.4 |
| MMLU-by-task - TruthfulQA MC1 | 34.64 | Accuracy (%) | 78.4 |
| MMLU-by-task - Virology | 46.39 | Accuracy (%) | 76.3 |
| MMLU-by-task - Abstract Algebra | 33 | Accuracy (%) | 75.6 |
| MMLU-by-task - TruthfulQA MC2 | 49.54 | Accuracy (%) | 73.9 |
| MMLU-by-task - HellaSwag | 61.97 | Accuracy (%) | 73.2 |
| MMLU-by-task - International Law | 71.9 | Accuracy (%) | 72.1 |
| MMLU-by-task - Conceptual Physics | 43.83 | Accuracy (%) | 71.7 |
| MMLU-by-task - Anatomy | 48.89 | Accuracy (%) | 71.6 |
| MMLU-by-task - Computer Security | 67 | Accuracy (%) | 71.5 |
| MMLU-by-task - ARC Challenge | 55.38 | Accuracy (%) | 70.9 |
Interactive version: theaggregate.ai/model?slug=openchat-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.