註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

EvoClaw-Bench
@evoclawbench
Evaluating frontier AI for long-horizon, continuous software engineering
加入 April 2026
6 正在關注    8 粉絲
🚀 The most realistic coding benchmark yet. The latest EvoClaw continuous & long-horizon coding leaderboard is out! This update features Opus 4.7 xhigh (200k/1m), GPT-5.4 xhigh, GLM-5.1, and GLM 5. (GPT-5.5 and Kimi-k2.6 are coming in the next update 👀)
顯示更多