List your company
ResearchFormerly WizWand

Question Answering on Overall Average (Acc., Rel., FC)

55AccuracyClaude Sonnet 4
19.6428.823847.18Jul 22, 2025
Updated 6mo ago

Evaluation results

MethodLinks
Claude Sonnet 4Model Category=Closed-source Models2025.07557524
GPT-4.1Model Category=Closed-source Models2025.07545842
Deliberative Searcher-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.0748759
GPT-4oModel Category=Closed-source Models2025.07417326
Deliberative Searcher-DeepSeek-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.0741759
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.0735752
R1-Searcher-7BModel Category=7B Models, Backbone=R1-7B2025.07344654
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B, Reward Function=ECE-based2025.0733743
Qwen2.5-VL-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07315841
InternVL3-78BModel Category=70B Models, Backbone=InternVL3-78B2025.07305346
DeepSeek-R1-Distill-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07304159
ReSearch-7BModel Category=7B Models2025.07263070
Search-R1-7BModel Category=7B Models, Backbone=R1-7B2025.07244949
Qwen2.5-VL-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07215248