List your company

General AI Assistant Tasks on GAIA Out-of-Distribution

47AccuracyClaude Sonnet 4
8.5218.5128.538.49Jul 22, 2025

Evaluation results

MethodLinks
Claude Sonnet 4Model Category=Closed-source Models2025.07477426
GPT-4.1Model Category=Closed-source Models2025.07374654
Deliberative Searcher-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.0735786
GPT-4oModel Category=Closed-source Models2025.07267723
Deliberative Searcher-DeepSeek-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07247811
R1-Searcher-7BModel Category=7B Models, Backbone=R1-7B2025.07203565
DeepSeek-R1-Distill-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07181684
ReSearch-7BModel Category=7B Models2025.07162278
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B, Reward Function=ECE-based2025.0716901
Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.0715891
Qwen2.5-VL-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07143961
Qwen2.5-VL-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07134357
InternVL3-78BModel Category=70B Models, Backbone=InternVL3-78B2025.07124852
Search-R1-7BModel Category=7B Models, Backbone=R1-7B2025.07104456