74.% on DeepSWE 1.1, big leaps on FrontierMath Tier 4, Terminal-Bench Science 0.1 and more.
Post #9196
1.35K


OPENAI 🔥: GPT-6 Astra scored 98.6% on ARC-AGI-3 and topped most of the other benchmarks.
- ❤ 15
- 👍 3