Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Browsing and Comparison on Browsecomp VL
Loading...
54.9
Accuracy
GPT-5
3.524
16.862
30.2
43.538
Mar 1, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5
Evaluation Paradigm=RA...
2026.03
54.9
GPT-5
Evaluation Paradigm=Di...
2026.03
48.6
MM-DeepResearch 32B
Evaluation Paradigm=Ag...
2026.03
43
MM-DeepResearch-8B
Evaluation Paradigm=Ag...
2026.03
37.9
SenseNova-MARS-8B
Evaluation Paradigm=Ag...
2026.03
35.1
Qwen3-VL-32B
Evaluation Paradigm=Ag...
2026.03
35.1
MM-DeepResearch-7B
Evaluation Paradigm=Ag...
2026.03
32.8
Qwen3-VL-32B
Evaluation Paradigm=Di...
2026.03
30.8
Qwen3-VL-8B
Evaluation Paradigm=RA...
2026.03
29.3
Qwen3-VL-8B
Evaluation Paradigm=Ag...
2026.03
27.9
WebWatcher-32B
Evaluation Paradigm=Ag...
2026.03
27
Qwen3-VL-8B
Evaluation Paradigm=Di...
2026.03
24.1
WebWatcher-7B
Evaluation Paradigm=Ag...
2026.03
21.2
MMSearch-R1-7B
Evaluation Paradigm=Ag...
2026.03
20.9
Visual-ARFT-7B
Evaluation Paradigm=Ag...
2026.03
16.5
GPT-4o
Evaluation Paradigm=RA...
2026.03
13.4
GPT-4o
Evaluation Paradigm=Di...
2026.03
5.5
Feedback
Search any
task
Search any
task