Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information Seeking Question Answering on InfoSeek
Loading...
73.9
Accuracy
MM-DeepResearch 32B
21.068
34.784
48.5
62.216
Mar 1, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
MM-DeepResearch 32B
Evaluation Paradigm=Ag...
2026.03
73.9
MM-DeepResearch-8B
Evaluation Paradigm=Ag...
2026.03
72.3
GPT-5
Evaluation Paradigm=RA...
2026.03
70.6
SenseNova-MARS-8B
Evaluation Paradigm=Ag...
2026.03
70.1
GPT-5
Evaluation Paradigm=Di...
2026.03
61.7
GPT-4o
Evaluation Paradigm=RA...
2026.03
59.5
MM-DeepResearch-7B
Evaluation Paradigm=Ag...
2026.03
58.7
Qwen3-VL-32B
Evaluation Paradigm=Ag...
2026.03
58.5
MMSearch-R1-7B
Evaluation Paradigm=Ag...
2026.03
55.1
GPT-4o
Evaluation Paradigm=Di...
2026.03
52.9
DeepEyes-v2-7B
Evaluation Paradigm=Ag...
2026.03
51.1
Qwen3-VL-8B
Evaluation Paradigm=Ag...
2026.03
50.3
DeepMMSearch-R1-7B
Evaluation Paradigm=Ag...
2026.03
47.5
Qwen3-VL-8B
Evaluation Paradigm=RA...
2026.03
46.1
Visual-ARFT-7B
Evaluation Paradigm=Ag...
2026.03
37.9
Qwen3-VL-32B
Evaluation Paradigm=Di...
2026.03
28
Qwen3-VL-8B
Evaluation Paradigm=Di...
2026.03
23.1
Feedback
Search any
task
Search any
task