Track Codex with GPT-6 Sol on SWE-Bench-Pro. A new high-reasoning baseline is being collected; degradation detection is paused.
0 comments
No comments yet.
Related stories
- GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligenceartificialanalysis.aiHacker News · 47 points · about 17 hours ago
- Hacker News · 4 points · 6 days ago
- Artifical Analysis - GPT-6.1 Sol Replaces 6 Sol After 7 Daysartificialanalysis.aiHacker News · 2 points · 1 day ago
- OpenAI says planned GPT-6.1 is too insecure to releasearstechnica.comArs Technica · 0 points · 1 day ago
- GPT-6 Sol (Max) Intelligence, Performance and Price Analysisartificialanalysis.aiHacker News · 2 points · 8 days ago
- Hacker News · 2 points · 7 days ago