allenai/reward-bench download history
allenai/reward-bench is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 10,213 times (2,446 in the last 7 days), and 658,668 times in total. It ranks #2,963 among datasets by monthly downloads.
Code | Leaderboard | Prior Preference Sets | Results | Paper Reward Bench Evaluation Dataset Card The RewardBench evaluation dataset evaluates capabilities of reward models over the following categories: Chat: Includes the easy chat subsets (alpacaeval-easy, alpacaeval-length, alpa
Models trained on reward-bench
13 models list it as training data.
- gyung/Qwev-9B-RLCD 69 downloads in 30 days
- mario-rc/multi-domain-rm-fsfairx-llama-3-8b-it 50 downloads in 30 days
- mario-rc/multi-domain-rm-fsfairx-gemma-2-9b-it 48 downloads in 30 days
- mario-rc/multi-domain-rm-skywork-llama-3.1-8b-it 40 downloads in 30 days
- mario-rc/multi-domain-rm-qwen-3-nemotron-8b-it 36 downloads in 30 days
- mario-rc/multi-domain-rm-mistral-7b-it 36 downloads in 30 days
- mario-rc/multi-domain-rm-skywork-qwen-3-8b-it 36 downloads in 30 days
- haizelabs/j1-micro-1.7B 35 downloads in 30 days
- samratduttaofficial/WaterSheep 32 downloads in 30 days
- Wonder-Griffin/autotrain-opengpt2-llmreward 24 downloads in 30 days
- haizelabs/j1-nano-0.6B 20 downloads in 30 days
- Shamima/dpo-implicit-reward – downloads in 30 days
Spaces using reward-bench
- Model Pulse 8 likes
Open allenai/reward-bench on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.