Skip to content
Can Agents Work
?
Atlas
Jobs
Benchmarks
Timeline
Sources
Method
Search
Benchmarks
/ Web research
Web research
Find hard-to-locate facts and answers on the web.
BrowseComp
by
OpenAI
Task level · Accuracy
92.2%
GPT-5.6 Sol Ultra · Jul 2026
Saturated
Finance Agent Benchmark
by
Vals AI
Task level · Accuracy
64.4%
Claude Opus 4.7 · 4 Jun 2026
Strong
GAIA
by
Meta
and
Hugging Face
Task level · Test-set accuracy
93.7%
Ops-Agentic-Search-2.0 · 22 Sep 2026
Saturated