#ModelScorePaper
1Skywork/Skywork-Reward-V2-Llama-3.1-8B84.13link
2ContextualAI/LMUnit-qwen2.5-72b82.08link
3ContextualAI/LMUnit-llama3.1-70b80.54link
4Databricks-Mosaic-Research/PGRM80.02link
5google/gemini-2.5-pro79.48link
6Skywork/Skywork-Reward-V2-Qwen3-8B78.37link
7google/gemini-2.5-flash77.67link
8nicolinho/QRM-Gemma-2-27B76.67link
9infly/INF-ORM-Llama3.1-70B76.48link
10anthropic/claude-opus-4-2025051476.48link
11allenai/Llama-3.1-70B-Instruct-RM-RB276.06link
12Skywork/Skywork-Reward-Gemma-2-27B75.76link
13Skywork/Skywork-Reward-V2-Qwen3-4B75.51link
14anthropic/claude-3-7-sonnet-2025021975.39link
15Skywork/Skywork-Reward-Gemma-2-27B-v0.275.31link
16Skywork/Skywork-Reward-V2-Llama-3.2-3B74.66link
17LxzGordon/URM-LLaMa-3.1-8B73.94link
18Schrieffer/Llama-SARM-4B73.79link
19Skywork/Skywork-Reward-Llama-3.1-8B73.14link
20allenai/Llama-3.1-8B-Instruct-RM-RB272.85link
21ShikaiChen/LDL-Reward-Gemma-2-27B-v0.172.49link
22openai/gpt-4.1-2025-04-1472.32link
23allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB272.20link
24Skywork/Skywork-Reward-Llama-3.1-8B-v0.271.75link
25anthropic/claude-sonnet-4-2025051471.17link
26nicolinho/QRM-Llama3.1-8B-v270.74link
27HFXM/RAMO-Llama3.1-8B69.17link
28Skywork/Skywork-VL-Reward-7B68.85link
29allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB268.71link
30allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB268.70link
RewardBench 2 rewardbench-2 Leaderboard