Browsecomp Score Correction: Sol Single-Agent Hits 90.4
nrehiew_ · x · 2026-07-17
Correction: Sol is actually SOTA on Browsecomp.
- Single-agent score is 90.4.
- Multi-agent score is 92.2.
The focus of this update isn't a new method, but an accurate correction of previous results, clarifying the score differences between the single-agent and multi-agent setups.
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26