model profile
Rank · overall#134
Score55.2
Benchmark scores
3 benchmarksCodingAgentBench48%Pass rate
WebDev Arena1358WebDev Elo · ± 8
BrowseComp63.8%Accuracy
Across harnesses
10 agentspiCLI
48%——
71Qwen CodeCLI
20%——
59AiderCLI
12%——
54Copilot CLICLI
12%——
54Codex CLICLI
0%——
34CrushTUI
0%——
34GooseCLI
0%——
34OpenCodeTUI
0%——
34OpenHandsAgent
0%——
34PlandexCLI
0%——
34Per-benchmark score · composite per harness. Tap a row to open that board.
Scraped and aggregated from public leaderboards · 2026-08-16