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 ...
Discover how DSPy is automating prompt engineering, transforming AI workflows, and helping businesses scale with precision and efficiency.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback