Updates
A dated record of everything that has changed on the board: model additions, re-runs, price corrections. Anchors stay stable, so entries can be cited.
- 2026-08-16
Site launch. 9 models scored on the 1,000-conversation set: Muse Spark, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT OSS 120B, GPT-5.3 Chat, GPT-5.5 Instant, GPT OSS 20B, GPT-5. Vendor price sheets checked the same day.
The live table is on the leaderboard, and each release of the results is downloadable from the data page.