Skip to content

DeepSWE: A Contamination-Resistant Coding Benchmark — James Shi, Datacurve

AI Engineer1.03M subscribers

4,251 views

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video

Introduces contamination-resistant coding benchmark methodology for evaluating AI code generation. Technical evaluation framework with reproducible approach.

Video by AI Engineer, played through YouTube's embedded player.

Part of Data (Datasets and RL Environments) @ AI Engineer, Evals & Benchmarks @ AI Engineer