Claude 3.7 Sonnet
Anthropic
rich detail 27 method fields published
Evaluation
RE-Bench subset
performance on a modified subset of METR's RE-Bench (triton_cumsum, rust_codecontests_inference, restricted_mlm, fix_embedding)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.