beaver-7B-v2.0-cost: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1422 ± 51, rank #5092 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench Safety | 76.08 | Accuracy (%) | 40.3 |
| RewardBench Prior Sets (0.5 weight) | 53.97 | Score (%) | 28.9 |
| RewardBench 2 Safety | 73.56 | Score (%) | 24.4 |
| RewardBench Chat Hard | 45.61 | Accuracy (%) | 20.2 |
| RewardBench Reasoning | 62.11 | Accuracy (%) | 17.8 |
| RewardBench | 59.57 | Score (%) | 14.8 |
| RewardBench 2 Factuality | 37.89 | Accuracy (%) | 6.9 |
| RewardBench 2 Precise IF | 27.5 | Score (%) | 6.7 |
| RewardBench 2 | 33.26 | Score (%) | 5.6 |
| RewardBench 2 Focus | 28.28 | Score (%) | 4.8 |
| RewardBench Chat | 57.26 | Accuracy (%) | 3.7 |
| RewardBench 2 Math | 33.33 | Score (%) | 3 |
Interactive version: theaggregate.ai/model?slug=beaver-7b-v2-0-cost · How It Works · Data refreshed daily, snapshot 2026-11-08.