Anthropic releases 'best coding model in the world'
Digest more
Chinese AI developer DeepSeek has released its "experimental" latest model, which it said was more efficient to train and ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results