Same AI model, 35-point swing from the harness
Why it matters
8090 Labs ran 7 models in 5 coding harnesses on DeepSWE v1.1: GLM 5.3 Flash passed 24% in Codex vs 59% in DeepSeek's harness, and no model did best in its maker's own harness. Test model + harness together and price by cost per success.
Read the source: 8090 Labs (opens in a new tab)
All hits from 13 Oct 2026More ModelsGet the daily hits by email