MMLU-Pro holds steady at 85.0, AIME 2025 slightly improves to 89.3, while GPQA-Diamond dips from 80.7 to 79.9. Coding and agent benchmarks tell a similar story, with Codeforces ratings rising from ...
To elevate AI up this abstraction ladder, the same needs to happen for the inputs it receives. We’ve seen this pattern before ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback