openchat_v3.2 [float16] [rev: 65320bf6dbe0]: benchmark results
Provider: OpenChat. Access: Open.
Aggregate Rating 1363 ± 34, rank #7354 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 82.68 | Normalized accuracy (%) (10-shot) | 53.1 |
| Open LLM Leaderboard v1 - WinoGrande | 76.95 | Accuracy (%) (5-shot) | 52 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.64 | Normalized accuracy (%) (25-shot) | 44.3 |
| Open LLM Leaderboard v1 - MMLU | 56.68 | Accuracy (%) (5-shot) | 39.7 |
| Open LLM Leaderboard v1 - GSM8K | 13.65 | Accuracy (%) (5-shot) | 35.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.49 | MC2 (%) (0-shot) | 27.4 |
Interactive version: theaggregate.ai/model?slug=openchat-v3-2-float16-rev-65320bf6dbe0 · How It Works · Data refreshed daily, snapshot 2026-11-08.