beaver-7B-v1.0-cost: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1410 ± 49, rank #5622 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench Prior Sets (0.5 weight) | 57 | Score (%) | 43.3 |
| RewardBench Safety | 73.51 | Accuracy (%) | 37.5 |
| RewardBench 2 Safety | 75.89 | Score (%) | 29 |
| RewardBench Chat Hard | 42.32 | Accuracy (%) | 13.9 |
| RewardBench | 57.98 | Score (%) | 11.9 |
| RewardBench Reasoning | 54.82 | Accuracy (%) | 10.7 |
| RewardBench 2 Math | 39.89 | Score (%) | 7.3 |
| RewardBench 2 | 33.32 | Score (%) | 6.1 |
| RewardBench Chat | 61.73 | Accuracy (%) | 5.7 |
| RewardBench 2 Factuality | 32.63 | Accuracy (%) | 5.2 |
| RewardBench 2 Focus | 29.39 | Score (%) | 5.2 |
| RewardBench 2 Ties | -1 | Score (%) | 1.3 |
Interactive version: theaggregate.ai/model?slug=beaver-7b-v1-0-cost · How It Works · Data refreshed daily, snapshot 2026-11-08.