Eurus-RM-7b
Eurus-RM-7b.
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Eurus-RM-7b
Open weights Small
No Epoch Capabilities Index score yet
- RewardBench 2 58.1% #32 /42
- M-RewardBench 67.3% #4 /9
- Preference Proxy Evaluations 60.4% #7 /9
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| M-RewardBench | 67.3% | #4 of 9 | Official leaderboard | |
| RewardBench | 81.6% | #25 of 48 | Official leaderboard | |
| RewardBench 2 | 58.1% | #32 of 42 | Official leaderboard | |
| Preference Proxy Evaluations | 60.4% | #7 of 9 | Official leaderboard |
Who measured it?
Independent runs cover all 4 of its benchmarks.
- An independent run only 4
Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards