top | item 44829716 (no title) attentive | 6 months ago > scoring 74.9% on SWE-bench Verified and 88% on Aider polyglotwhy isn't it on https://aider.chat/docs/leaderboards/?"last updated August 07, 2025" discuss order hn newest tedsanders|6 months ago The 88% is our self-reported score on our internal implementation of Aider polyglot.The leaderboard score would come from Aider independently running GPT-5 themselves. The score should be about the same.(I work at OpenAI.)
tedsanders|6 months ago The 88% is our self-reported score on our internal implementation of Aider polyglot.The leaderboard score would come from Aider independently running GPT-5 themselves. The score should be about the same.(I work at OpenAI.)
tedsanders|6 months ago
The leaderboard score would come from Aider independently running GPT-5 themselves. The score should be about the same.
(I work at OpenAI.)