Benchmark Almanac

Skywork-Reward-Llama-3.1-8B-v0.2

Skywork-Reward-Llama-3.1-8B-v0.2.

Skywork AI (Kunlun Tech) Released October 14th, 2024 Family Skywork-Reward 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
Skywork AI (Kunlun Tech) Oct 2024

Skywork-Reward-Llama-3.1-8B-v0.2

Open weights Small

No Epoch Capabilities Index score yet
  • RewardBench 2 71.8% #17 /42
  • RewardBench 93.1% #4 /48
  • LegalRewardBench 67% #27 /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 93.1% #4 of 48 Official leaderboard
RewardBench 2 71.8% #17 of 42 Official leaderboard

Professional work

BenchmarkScoreRankSource
LegalRewardBench 67% #27 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