openchat-3.5-1210: benchmark results
OpenChat's openchat-3.5-1210, a Mistral 7B fine-tune with separate Coding+Generalist and Mathematical Reasoning modes, plus experimental evaluator and feedback capabilities. Provider: OpenChat. Released 2023-12-10. Access: Open.
Aggregate Rating 1449 ± 20, rank #1004 of 1656 rated models, from 46 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 65.96 | Accuracy (%) (5-shot) | 81 |
| Open LLM Leaderboard - MuSR | 44.14 | Score | 78.8 |
| Open LLM Leaderboard v1 - WinoGrande | 80.74 | Accuracy (%) (5-shot) | 75.4 |
| Open LLM Leaderboard v1 - MMLU | 64.62 | Accuracy (%) (5-shot) | 73.5 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 52.96 | Accuracy (%) | 73.4 |
| Open PL LLM - KLEJ NER (generative, 5-shot) | 52.77 | Accuracy (%) | 72.5 |
| Open LLM Leaderboard - IFEval | 60.37 | Score | 72.3 |
| Open LLM Leaderboard v1 - HellaSwag | 84.92 | Normalized accuracy (%) (10-shot) | 70.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.93 | Normalized accuracy (%) (25-shot) | 68.5 |
| Open PL LLM - DYK (generative, 5-shot) | 61.97 | Binary F1 (%) | 67.6 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 59.63 | Binary F1 (%) | 67.1 |
| Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot) | 72.06 | Accuracy (%) | 66.5 |
Interactive version: theaggregate.ai/model?slug=openchat-3-5-1210 · How It Works · Data refreshed daily, snapshot 2026-10-20.