What it does
Open benchmark for coding-agent harnesses. v1.1 covers 21 harnesses × 5 open models × 62 tasks, reporting pass rate and cost per pass.
Source: ai.jenquist.com
Reading
- “Swarm Riders” Claim 600M Tokens a Day AI Digest · 2026-11-11
FrontierHarness Eval is an evaluation resource for measuring AI agent swarms. Open benchmark for coding-agent harnesses. v1.1 covers 21 harnesses × 5 open models × 62 tasks, reporting pass rate and cost per pass.
FrontierHarness Eval is the marked particle among the 19 tools
Open benchmark for coding-agent harnesses. v1.1 covers 21 harnesses × 5 open models × 62 tasks, reporting pass rate and cost per pass.
Source: ai.jenquist.com