tulu-2-70B: benchmark results
Provider: Allen AI. Access: Open.
Aggregate Rating 1457 ± 39, rank #3453 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Finetuning with Scientific Data Increases Hall | 65.6 | OFS (self-reported) | 76.5 |
| JustEval - Factuality | 4.78 | Score (1-5) | 66.7 |
| JustEval - Helpfulness | 4.77 | Score (1-5) | 66.7 |
| JustEval - Clarity | 4.95 | Score (1-5) | 63.3 |
| Open CoT - LogiQA 2 | 8.84 | CoT Gain (%) | 62.6 |
| Open CoT - LSAT Logical Reasoning | 12.75 | CoT Gain (%) | 62.2 |
| Open CoT Leaderboard | 7.52 | Average CoT Gain (%) | 53.4 |
| Open CoT - LSAT Reading Comprehension | 11.15 | CoT Gain (%) | 46.9 |
| JustEval | 4.7 | Avg Score (1-5) | 46.7 |
| JustEval - Depth | 4.32 | Score (1-5) | 46.7 |
| Open CoT - LSAT Analytical Reasoning | 2.61 | CoT Gain (%) | 34 |
| Open CoT - LogiQA | 2.24 | CoT Gain (%) | 27.9 |
Interactive version: theaggregate.ai/model?slug=tulu-2-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.