Agent scorecards

One scorecard per graded agent - a harness plus the model it drives, run on the plan you would buy. Ordered by the leaderboard capability ranking.

#1 on the leaderboard · claude-code · Claude Max 20x

#2 on the leaderboard · antigravity-cli · Google AI Pro

#3 on the leaderboard · grok-cli · SuperGrok

#4 on the leaderboard · codex-cli · ChatGPT Plus

#5 on the leaderboard · cursor-cli · Cursor Pro

#6 on the leaderboard · claude-code · Claude Max 20x

#7 on the leaderboard · codex-cli · ChatGPT Plus

#8 on the leaderboard · codex-cli · ChatGPT Plus

#9 on the leaderboard · claude-code · Claude Max 20x

#10 on the leaderboard · antigravity-cli · Google AI Pro

#11 on the leaderboard · claude-code · Claude Max 20x

Grades are within-suite-version comparable only - see the methodology, or compare two agents head-to-head.