List your company

Question Answering on MuSiQue (In-Distribution)

44AccuracyClaude Sonnet 4
10.7219.362836.64Jul 22, 2025

Evaluation results

MethodLinks
Claude Sonnet 4Model Category=Closed-source Models2025.07445742
GPT-4.1Model Category=Closed-source Models2025.07434555
Deliberative Searcher-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07377114
Deliberative Searcher-DeepSeek-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07347211
GPT-4oModel Category=Closed-source Models2025.07335247
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.0729742
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B, Reward Function=ECE-based2025.0727712
R1-Searcher-7BModel Category=7B Models, Backbone=R1-7B2025.07263565
Qwen2.5-VL-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07255049
InternVL3-78BModel Category=70B Models, Backbone=InternVL3-78B2025.07244158
DeepSeek-R1-Distill-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07233268
ReSearch-7BModel Category=7B Models2025.07182278
Search-R1-7BModel Category=7B Models, Backbone=R1-7B2025.07164553
Qwen2.5-VL-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07124852