Reward Modeling on SCAN HPD
82.88Accuracygemini-2.5-pro
Evaluation results
| Method | Links | |
|---|---|---|
| gemini-2.5-proModel Category=Base Models (LLM-as-a-Judge)2026.01 | 82.88 | |
| deepseek-r1-0528Model Category=Base Models (LLM-as-a-Judge)2026.01 | 82.27 | |
| gpt-5-2025-08-07Model Category=Base Models (LLM-as-a-Judge)2026.01 | 81.47 | |
| o3-2025-04-16Model Category=Base Models (LLM-as-a-Judge)2026.01 | 81.47 | |
| qwen-plus-latestModel Category=Base Models (LLM-as-a-Judge)2026.01 | 80.48 | |
| RM-NLHF-Qwen-32BModel Category=Our Generative Reward Models, Backbone=Qwen-32B2026.01 | 78.88 | |
| qwen3-maxModel Category=Base Models (LLM-as-a-Judge)2026.01 | 78.65 | |
| RM-R1-Qwen-32BModel Category=Specialized Generative Reward Models, Backbone=Qwen-32B2026.01 | 77.95 | |
| INF-ORM-Llama3.1-70BModel Category=Scalar Reward Models, Backbone=Llama-3.1-70B2026.01 | 76.84 | |
| deepseek-v3Model Category=Base Models (LLM-as-a-Judge)2026.01 | 76.36 | |
| RRM-Qwen-32BModel Category=Specialized Generative Reward Models, Backbone=Qwen-32B2026.01 | 76.04 | |
| gpt-4o-latestModel Category=Base Models (LLM-as-a-Judge)2026.01 | 75.72 | |
| claude-3-7-sonnet-20250219Model Category=Base Models (LLM-as-a-Judge)2026.01 | 75.24 | |
| R1-Distill-Qwen-32BModel Category=Base Models (LLM-as-a-Judge), Backbone=Qwen-32B2026.01 | 74.92 | |
| Skywork-Reward-Llama-3.1-8B-v0.2Model Category=Scalar Reward Models, Backbone=Llama-3.1-8B2026.01 | 72.05 | |
| URM-LLaMa-3.1-8BModel Category=Scalar Reward Models, Backbone=Llama-3.1-8B2026.01 | 70.13 | |
| RM-NLHF-Qwen-7BModel Category=Our Generative Reward Models, Backbone=Qwen-7B2026.01 | 68.22 | |
| RRM-Qwen-7BModel Category=Specialized Generative Reward Models, Backbone=Qwen-7B2026.01 | 66.45 | |
| ArmoRM-Llama3-8B-v0.1Model Category=Scalar Reward Models, Backbone=Llama3-8B2026.01 | 66.28 | |
| R1-Distill-Llama-8BModel Category=Base Models (LLM-as-a-Judge), Backbone=Llama-8B2026.01 | 65.92 | |
| RM-R1-Qwen-7BModel Category=Specialized Generative Reward Models, Backbone=Qwen-7B2026.01 | 64.38 | |
| DeepSeek-R1-Distill-Qwen-7BModel Category=Base Models (LLM-as-a-Judge), Backbone=Qwen-7B2026.01 | 60.15 |