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 ...
NetEase-backed study shows language model agents may detect bugs faster and with greater coverage than existing tools.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback