model profile
Rank · overall#98
Score58.5
Benchmark scores
6 benchmarksSWE-bench Verified79.4%% Resolved · 2026-05-19
Chatbot Arena (Coding)1505Coding Elo
Artificial Analysis46Intelligence Index
AA Coding Index66Coding Index
Arena Agent0.09%Net Improvement · ± 1.07
FrontierMath (Tier 4)34.1%Accuracy · ± 7.5
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