Skip to content

Leaderboard
Rank Pass@1 Pass@3 Submission
#1 claude-opus-4-6
(claude-code)
2026-03-24 51.5 24.5 19.2 58.3 31.9 26.1
#2 kimi-k2.5
(opencode)
2026-03-25 45.1 7.4 4.6 62.3 20.4 15.5
#3 gpt-5.3-codex
(codex-cli)
2026-03-24 29.9 6.9 4.8 40.7 15.7 14.5
#4 gemini-2.5-pro
(gemini-cli)
2026-03-24 25.0 7.8 5.5 34.8 15.7 13.5
#5 glm-5
(opencode)
2026-03-25 61.7 1.9 2.4 64.2 3.1 2.9