openchat_8192: benchmark results
Provider: OpenChat. Access: Open.
Aggregate Rating 1287 ± 15, rank #8896 of 10916 rated models, from 70 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 38 | Accuracy (%) | 96.5 |
| MMLU-by-task - HellaSwag | 62.72 | Accuracy (%) | 79.2 |
| MMLU-by-task - ARC Challenge | 56.66 | Accuracy (%) | 77.8 |
| MMLU-by-task - Global Facts | 37 | Accuracy (%) | 76.3 |
| MMLU-by-task - Formal Logic | 35.71 | Accuracy (%) | 72.7 |
| MMLU-by-task - TruthfulQA MC1 | 31.82 | Accuracy (%) | 65.9 |
| MMLU-by-task - Medical Genetics | 56 | Accuracy (%) | 65.3 |
| MMLU-by-task - Computer Security | 65 | Accuracy (%) | 65 |
| MMLU-by-task - High School Microeconomics | 50.42 | Accuracy (%) | 63.7 |
| MMLU-by-task - Professional Accounting | 38.65 | Accuracy (%) | 62.8 |
| MMLU-by-task - Virology | 43.37 | Accuracy (%) | 62.8 |
| MMLU-by-task - Human Sexuality | 58.78 | Accuracy (%) | 62.2 |
Interactive version: theaggregate.ai/model?slug=openchat-8192 · How It Works · Data refreshed daily, snapshot 2026-11-08.