Hacker News new | past | comments | ask | show | jobs | submit
goldenarm | on: Kimi K2.7-Code: open-source coding model with better token efficiency
Benchmark geometric mean

- GPT-5.5: 62.7%

- Opus 4.8: 62.2%

- Kimi K2.7 Code: 56.3%

- Kimi K2.6: 48.2%

lostmsu | parent
Would be nice to have 5.2 and 4.6 for comparison.