BTRM_Qwen2.7b_0613: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1566 ± 34, rank #1468 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench Chat | 97.49 | Accuracy (%) | 90.1 |
| RewardBench Safety | 90.14 | Accuracy (%) | 82.4 |
| RewardBench Prior Sets (0.5 weight) | 70.29 | Score (%) | 80.4 |
| RewardBench 2 Ties | 65.27 | Score (%) | 66.3 |
| RewardBench Reasoning | 87.75 | Accuracy (%) | 65.1 |
| RewardBench | 81.72 | Score (%) | 60.8 |
| RewardBench Chat Hard | 57.24 | Accuracy (%) | 38.4 |
| RewardBench 2 Precise IF | 35.63 | Score (%) | 34.9 |
| RewardBench 2 Math | 60.66 | Score (%) | 34.7 |
| RewardBench 2 | 57.36 | Score (%) | 26 |
| RewardBench 2 Focus | 57.37 | Score (%) | 19.2 |
| RewardBench 2 Safety | 71.78 | Score (%) | 18.5 |
Interactive version: theaggregate.ai/model?slug=btrm-qwen2-7b-0613 · How It Works · Data refreshed daily, snapshot 2026-11-08.