openchat_v3.1 [bfloat16] [rev: cc708183e430]: benchmark results
Provider: OpenChat. Access: Open.
Aggregate Rating 1364 ± 34, rank #7340 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 82.84 | Normalized accuracy (%) (10-shot) | 54.1 |
| Open LLM Leaderboard v1 - WinoGrande | 76.24 | Accuracy (%) (5-shot) | 47 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.15 | Normalized accuracy (%) (25-shot) | 46.6 |
| Open LLM Leaderboard v1 - MMLU | 56.84 | Accuracy (%) (5-shot) | 40 |
| Open LLM Leaderboard v1 - GSM8K | 13.8 | Accuracy (%) (5-shot) | 35.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.38 | MC2 (%) (0-shot) | 27 |
Interactive version: theaggregate.ai/model?slug=openchat-v3-1-bfloat16-rev-cc708183e430 · How It Works · Data refreshed daily, snapshot 2026-11-08.