model profile
Rank · overall#54
Score67.2
Benchmark scores
6 benchmarksSWE-bench Verified79.8%% Resolved · 2026-07-21
Chatbot Arena (Coding)1535Coding Elo
Arena Agent2.36%Net Improvement · ± 1.22
WebDev Arena1537WebDev Elo · ± 9
FrontierMath (Tier 4)22%Accuracy · ± 6.5
MathArena Apex26%Accuracy
Across harnesses
0 agentsThis model appears only in model-level benchmarks — no harness ran it directly.
Scraped and aggregated from public leaderboards · 2026-08-16