Updates

Every change to the leaderboard, dated: models added, re-runs, and price corrections. Each entry keeps a stable anchor.

• 2026-08-16

  Initial release. 9 models evaluated on the 525-task set: Claude Fable 5, GPT-5.6 Sol, Claude Opus 5, Claude Sonnet 5, GPT-5.6 Terra, Claude Opus 4.8, GPT-5.6 Luna, GPT-5.5 Instant, MAI-Thinking-1. List prices verified against vendor price sheets on this date.

The current table is on the leaderboard; versioned downloads are on the data page.