26,040 Agent Runs Test Whether Switching Models Means Switching Harnesses
The FrontierHarness leaderboard v1.1 runs a 21-harness × 5-model × 62-task × 4-attempt matrix—26,040 agent runs and up to 100 billion tokens—to answer whether switching models should also mean switching harnesses.
2026-11-11 ~ 2026-11-11 · 2 related posts
- 26,040 agent runs and 100B tokens: FrontierHarness v1.1 ranks harnesses across 5 models — stuffyokodraws · 2026-11-11
- 26,040 agent runs across 21 harnesses and 5 open models: does switching models mean switching harnesses? — Double-Entertainer62 · 2026-11-11