Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web-browsing Agent Performance on BrowseComp-Plus 100k documents (100-query sample)
Loading...
77
Accuracy
gpt-5.4-mini (medium effort)
63.48
66.99
70.5
74.01
Jun 5, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
gpt-5.4-mini (medium effort)
Architecture=RISE-BM25
2026.06
77
mimo-v2.5-pro
Architecture=RISE-BM25
2026.06
75
mimo-v2.5-pro
Architecture=retrieval...
2026.06
73
gpt-5.4-nano (high effort)
Architecture=DCI
2026.06
71
gpt-5.4-mini (medium effort)
Architecture=retrieval...
2026.06
68
gpt-5.4-nano (high effort)
Architecture=retrieval...
2026.06
65
gpt-5.4-nano (high effort)
Architecture=RISE-BM25
2026.06
64
Feedback
Search any
task
Search any
task