tulu-2-dpo-7B-ExPO: benchmark results
Provider: chujiezheng. Access: Open.
Aggregate Rating 1346 ± 29, rank #7794 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.41 | MC2 (%) (0-shot) | 73.7 |
| Open LLM Leaderboard v1 - HellaSwag | 81.36 | Normalized accuracy (%) (10-shot) | 44.7 |
| Open LLM Leaderboard v1 - GSM8K | 26.38 | Accuracy (%) (5-shot) | 44.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.28 | Normalized accuracy (%) (25-shot) | 39.4 |
| Open LLM Leaderboard v1 - WinoGrande | 74.19 | Accuracy (%) (5-shot) | 35.4 |
| Open LLM Leaderboard v1 - MMLU | 52.23 | Accuracy (%) (5-shot) | 31.5 |
| AlpacaEval 2.0 | 11.68 | LC Win Rate (%) | 29.3 |
Interactive version: theaggregate.ai/model?slug=tulu-2-dpo-7b-expo · How It Works · Data refreshed daily, snapshot 2026-11-08.