airoboros-70B-3.3: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1503 ± 31, rank #2304 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 79.31 | Accuracy (%) (5-shot) | 99.4 |
| Open LLM Leaderboard v1 - GSM8K | 73.84 | Accuracy (%) (5-shot) | 98.9 |
| Open LLM Leaderboard v1 - WinoGrande | 84.37 | Accuracy (%) (5-shot) | 93.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.67 | Normalized accuracy (%) (25-shot) | 89.9 |
| Open Chinese LLM - CMMLU | 68.04 | Accuracy (%) | 79 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.68 | MC2 (%) (0-shot) | 74.1 |
| Open LLM Leaderboard v1 - HellaSwag | 85.27 | Normalized accuracy (%) (10-shot) | 73.2 |
| Open Chinese LLM - C-Eval Semantic | 77.79 | Accuracy (%) | 66.3 |
| Open Chinese LLM - HellaSwag | 61.36 | Accuracy (%) | 62.1 |
| Open Chinese LLM Leaderboard | 58.49 | Official Nonzero-Task Mean (%) | 61.8 |
| Open Chinese LLM - TruthfulQA MC | 52.88 | Accuracy (%) | 43.2 |
| Open Chinese LLM - GSM8K | 37.23 | Accuracy (%) | 34 |
Interactive version: theaggregate.ai/model?slug=airoboros-70b-3-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.