Benchmark Almanac

Llama-3.1-8B-Instruct-RM-RB2

Llama-3.1-8B-Instruct-RM-RB2.

Ai2 Released June 2nd, 2025 Family RewardBench-2-RMs The lab's model card Compare with others
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Ai2 Jun 2025

Llama-3.1-8B-Instruct-RM-RB2

Open weights Small

No Epoch Capabilities Index score yet
  • RewardBench 2 72.8% #14 /42
  • RewardBench 88.8% #10 /48
  • LegalRewardBench 68.9% #25 /29

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

BenchmarkScoreRankSource
RewardBench 88.8% #10 of 48 Official leaderboard
RewardBench 2 72.8% #14 of 42 Official leaderboard

Professional work

BenchmarkScoreRankSource
LegalRewardBench 68.9% #25 of 29 Official leaderboard

Who measured it?

Independent runs cover all 3 of its benchmarks.

  • An independent run only 3
Official leaderboards scored it on 3.

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards