{"slug":"hashgraph-online-ai-agent-bench","source_name":"hashgraph-online/ai-agent-bench","name":"Hashgraph Online/AI Agent Bench","description":"Compare Claude Code and Codex on the same real code-change task with isolated worktrees, identical gates, transcripts, time, and cost.","version":1,"lift":{"pass_rate_delta_pts":59.09,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":-49.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-02T05:44:21.292636+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":59.09,"with_pass_pct":81.8,"without_pass_pct":22.7,"tokens_delta_pct":-49.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":19,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-02T05:44:21.292636+00:00","run_id":"16c1b306-3f5a-446d-bc1c-f4cd723100bb","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"1c897ad8025b693287a1c2b009aa71644ca2bdabd7ac7c8de847434ba415520e","raw_url":"https://app.decimal.ai/s/hashgraph-online-ai-agent-bench/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/hashgraph-online-ai-agent-bench"}