model profile
Rank · overall#8
Score86.3
Benchmark scores
2 benchmarksFrontierMath (Tier 4)78%Accuracy · ± 6.5
BrowseComp90.1%Accuracy
Across harnesses
0 agentsThis model appears only in model-level benchmarks — no harness ran it directly.
Scraped and aggregated from public leaderboards · 2026-07-23