model profile
Rank · overall#37
Score69.6
Benchmark scores
10 benchmarksSWE-bench Verified76.2%% Resolved · 2025-12-17
Chatbot Arena (Coding)1469Coding Elo
ARC-AGI31.1%Score
Arena Agent8.65%Net Improvement · ± 0.76
WebDev Arena1437WebDev Elo · ± 8
FrontierMath (Tier 4)17.1%Accuracy · ± 5.9
SWE-bench Pro34.6%% Resolved
SWE-bench Multilingual72.7%% Resolved · 2026-02-13
SkillsBench54.6Score
MathArena Apex15.6%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