Link:hkinsley.com
Terminal-Bench v2.1: Why Agent Harnesses Determine LLM Benchmark Performance
New benchmarks on Terminal-Bench v2.1 demonstrate that agent harnesses fundamentally shift model rankings: DeepSeek-V4-Flash 0731 surged from a 49.4% pass rate on stock tooling to 71.9% under the OMP harness, drawing nearly level with GLM 5.2 (73.0%).
From Video: Weekly AI Updates: Model Releases, Agent Harnesses, and Developer Tooling (August 2026)

