Reward Modeling on IFBench Simple
87.2AccuracySkywork-Reward-Gemma-2-27B
Evaluation results
| Method | Links | |
|---|---|---|
| Skywork-Reward-Gemma-2-27B2025.02 | 87.2 | |
| GPT-4o2025.02 | 85.1 | |
| REWARDAGENT_MINISearch Engine=true2025.02 | 85.1 | |
| o3-mini2025.02 | 81.9 | |
| INF-ORM-Llama3.1-70B2025.02 | 78.7 | |
| Skywork-Reward-Llama-3.1-8B-v0.22025.02 | 78.7 | |
| REWARDAGENT_MINISearch Engine=false2025.02 | 78.7 | |
| internlm2-7b-reward2025.02 | 74.5 | |
| internlm2-20b-reward2025.02 | 74.5 | |
| REWARDAGENT_LLAMASearch Engine=true2025.02 | 74.5 | |
| ArmoRM-Llama3-8B-v0.12025.02 | 72.3 | |
| DeepSeek-R12025.02 | 72.3 | |
| GPT-4o mini2025.02 | 70.2 | |
| REWARDAGENT_LLAMASearch Engine=false2025.02 | 70.2 | |
| DeepSeek-R1-Distill-Llama-8B2025.02 | 53.2 | |
| Llama3-8B Instruct2025.02 | 12.8 |