5 tagged ai benchmark, measured the same way as everything else here.
Instructions file CodexOpenCode
Instructions for ktwu01/benchmark-radar, covering repository instructions, glob rule: showcase and ui communication, example: simplify badge copy and keep its style, glob rule: benchmark radar audience and pull request merges.
Instructions file
Instructions for ktwu01/benchmark-radar, a project described as: Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.
Instructions file CodexOpenCode
Instructions for MetriLLM/metrillm, covering agents.md — metrillm cli (metrillm/metrillm), project overview, project structure, commands and coding conventions.
Instructions file
Instructions for MetriLLM/metrillm, covering claude.md, project, commands, architecture and database.
Instructions file
Claude Code instructions for vvsotnikov/astro-bench, covering astro-bench — paper writing & orchestration, project structure, the paper, working with the paper and launching agent experiments.