List your company

Information Extraction on xbench-deepsearch Out-of-Distribution

47AccuracyClaude Sonnet 4
10.620.0529.538.95Jul 22, 2025

Evaluation results

MethodLinks
Claude Sonnet 4Model Category=Closed-source Models2025.07477129
GPT-4.1Model Category=Closed-source Models2025.07384357
Deliberative Searcher-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.0735779
GPT-4oModel Category=Closed-source Models2025.07326931
InternVL3-78BModel Category=70B Models, Backbone=InternVL3-78B2025.07245347
Qwen2.5-VL-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07236039
Deliberative Searcher-DeepSeek-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.0718808
R1-Searcher-7BModel Category=7B Models, Backbone=R1-7B2025.07173663
ReSearch-7BModel Category=7B Models2025.07172377
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B, Reward Function=ECE-based2025.0716861
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.0715861
Search-R1-7BModel Category=7B Models, Backbone=R1-7B2025.07144852
DeepSeek-R1-Distill-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07144060
Qwen2.5-VL-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07125842