heretical · Kimi K3 run 2

42.4Library score
Pass rate86.0%
Simplicity56.8
Problems $$11.32
Library $$5.38
The library
heretical · designed by Kimi K3 (mini-SWE)2,777 source lines
ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE87.2%57.3$3.90
43.8
GLM 5.3 Flash · mini-SWE84.1%56.6$4.94
40.3
GPT-5.6 Luna · Codex86.8%56.6$2.48
43.1
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
note-import48.764.253.255.4techdocs-render42.457.047.949.1editor-import74.637.072.461.3attachment-paste28.132.947.236.1trusted-markdown33.028.015.625.5diagram-preview40.627.434.134.0matrix-message54.339.153.448.9notebook-output48.655.246.049.9email-render32.532.819.128.2svg-ingest21.126.430.225.9collection-render36.035.342.237.9api-docs36.025.629.530.4post-enrich31.414.235.527.0learning-outcome54.858.944.152.6package-panel35.837.036.436.4poll-export82.381.872.478.8reader-extract55.562.065.861.1article-extract39.028.834.834.2timeline-render40.035.131.535.5brand-svg38.536.149.741.5telegram-notify32.022.237.730.6story-markdown59.250.648.852.8