Benchgen

StrongREJECT — Results

RankModelScore
1kimi-k2-699.8
2kimi-k2-599.5
3claude-fable-598.7
4nemotron-3-ultra-550b-a55b98.7
5deepseek-v4-pro98.6
6inkling98.6
7glm-5-298.5
8gpt-5-6-sol98.5
9gemini-3-1-pro98

StrongREJECT — Leaderboard

1 phaseActive

StrongREJECT Leaderboard

No self-reported entries.