OnlySOTA

Frontier AI model leaderboards with the kill line

Two boards averaged read as one that agrees. Nothing here is averaged — the disagreement is the reading.

Ranking · AA 17–53 · ARENA 1396–1510
  1. 153.4
  2. 252.81480
  3. 350.71493
  4. 449.71506
  5. 548.2
  6. 647.11483
  7. 744.91483
  8. 844.41456
  9. 943.81485
  10. 1042.31466
  11. 11Retired42.01481
  12. 1241.91475
  13. 1341.2
  14. 14Retiredest40.71502
  15. 1540.31481
  16. 1639.9
  17. 1739.81500
  18. 18est39.61490
  19. 19NewUnmatched39.5
  20. 2039.11468
  21. 21Retiredest39.01476
  22. 22Retired38.61482
  23. 2338.41461
  24. 2437.51452
  25. 2536.31463
  26. 26NewUnmatchedExecutionerest35.5
More — all 371 entries on AA's board →
Kill line · index × price
ARTIFICIAL ANALYSIS INTELLIGENCE INDEX · linear from 020400$0.05$0.25$1.00$5.0053.4$20.00Claude Fable 5.1ExecutionerAgnes 3.0 Flash35.5 · $0.07 · estSOTALOW-COSTKILLEDBLENDED PRICE, USD PER 1M TOKENS (3:1 INPUT:OUTPUT) · LOG10
Kill lineFrontier — nothing beats these on both axesSOTALow-costKilledHollow, or a faint cross — estimated by the source

Claude Fable 5.1

anthropic/claude-fable-5-1 · closed · $20.00 · SOTA

2sources
6entries
6configs
Where it places · 2 sources
Artificial Analysis LLM Leaderboard53.4
1Arena — Agent0.139

Bars are drawn on each source's own fitted range, so position is not comparable between rows. The rank is the source's own, and a source that publishes none gets neither a number nor a bar.

Effort ladder · 6 configs
Artificial Analysis LLM Leaderboardmax wins
minlowmedhighxhimax47.049.151.253.253.4
Arena — Agent · agentonly max ran
minlowmedhighxhimax0.139

Six named efforts, same columns on every track; a greyed name is a configuration this source did not publish. Scores are each source's own and are not compared across tracks.