Tool Use & Agents · sub-racePhoto finish
Web Research race
Finding hard-to-locate facts by browsing, searching and cross-checking many sources.
- Leader
- Fable 5.1
- Margin
- 0.5 pts
- 0.6% ahead
- Weeks at #1
- 9
- in a row
- Changes
- 4
- in 2026
Warming up the track…
Oct 19, 2026Fable 5.1 leads
2025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26
Score history
Top 6 today over the leader's frontier · click to jump to a week
#1 frontierFable 5.1GPT-6 AstraOpus 5.5GPT-6.1 SolGemini 4 ArgonGrok 4.7
Reigns at #1
Longest: Grok 4, 18 weeks (from Jul 2025).
Sibling races
More tool use & agents races
Why this race matters
Deep research is one of the most-used agent products.
How it is scored
Accuracy on browse-only questions.
Unit: percentHigher is betterPhoto finish under 0.5 ptsDominant over 3.0 pts
Data provenance
BrowseComp
Questions that require persistent multi-hop browsing.
Scores here are illustrative placeholders that mimic real benchmark patterns. Swap in live data through the score provider. Methodology