Every AI leaderboard, side by side

Leaderboards28Models ranked835

gpt-transcribe (openai) vs Claude Fable 5.1 vs Kimi K3

One row per board where at least one is ranked, from each board's current capture.

  • gpt-transcribe (openai)
  • Claude Fable 5.1
  • Kimi K3

Head to head on 10 boards: Claude Fable 5.1 places best on 9, Kimi K3 places best on 1 and gpt-transcribe (openai) places best on 0. All 3 ranked on 0 of 16 boards.

Two at a time on this screen. Tap one to swap it in.

Boardgpt-transcribe (openai)Claude Fable 5.1Kimi K3
Chat1
Text ArenaArena ratingyesterday#61,501best of the picked#131,488
Reasoning6
LiveBenchGlobal averageyesterday#183.4%best of the picked#1379.2%
AA IntelligenceIndexyesterday#353.4best of the picked#1343.6
Epoch ECIECIyesterday#5164.7best of the picked#15157.4
ARC-AGI-2Scoreyesterday#690.0%best of the picked#2960.4%
HLEAccuracyyesterday#246.5%
GPQA DiamondAccuracyyesterday#1893.1%
Coding2
SWE-Bench ProResolvedyesterday#292.2%best of the picked#488.2%
WebDev ArenaArena ratingyesterday#51,749best of the picked#101,658
Agents and tools1
MCP AtlasPass rateyesterday#287.2%best of the picked#882.3%
Vision2
Document ArenaArena ratingyesterday#21,513
Vision ArenaArena ratingyesterday#131,288
Speech1
Open ASRAverage WERyesterday#204.57 WER
Speed1
AA SpeedOutput speedyesterday#1568 tok/sbest of the picked#2536 tok/s
Price1
AA PriceBlended priceyesterday#24$20.0#22$6.00best of the picked
Usage1
OpenRouterWeekly tokensyesterday#151.7T tok

Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.

More comparisons