LeadersPodium wallBoardsModelsCompareBenchmarksLabsWhat changedMethod

Every AI leaderboard, side by side

Leaderboards28Models ranked835

K2 Think V2 vs Gemini 3.8 Flash vs Muse Spark vs GPT-6 Astra

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

ModelsVendorsOpen vs closed
  • K2 Think V2
  • Gemini 3.8 Flash
  • Muse Spark
  • GPT-6 Astra

Head to head on 14 boards: GPT-6 Astra places best on 9, Gemini 3.8 Flash places best on 4, Muse Spark places best on 1 and K2 Think V2 places best on 0. All 4 ranked on 0 of 16 boards.

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

BoardK2 Think V2Gemini 3.8 FlashMuse SparkGPT-6 Astra
Chat2
Text ArenaArena ratingyesterday#71,495best of the picked#121,489#261,477
MultiChallengeScoreyesterday#175.5%
Reasoning6
HLEAccuracyyesterday#444.5%#640.6%#154.8%best of the picked
GPQA DiamondAccuracyyesterday#395.4%#4189.8%#195.8%best of the picked
Epoch ECIECIyesterday#20156.7#44152.0#2166.4best of the picked
AA IntelligenceIndexyesterday#9011.5#1640.9#452.7best of the picked
ARC-AGI-2Scoreyesterday#889.2%#195.0%best of the picked
LiveBenchGlobal averageyesterday#3275.8%#482.2%best of the picked
Coding2
WebDev ArenaArena ratingyesterday#251,583#21,788best of the picked
SWE-Bench ProResolvedyesterday#958.8%#390.2%best of the picked
Agents and tools1
MCP AtlasPass rateyesterday#982.2%
Vision2
Vision ArenaArena ratingyesterday#91,290#61,294best of the picked#181,284
Document ArenaArena ratingyesterday#241,444#131,468best of the picked
Speed1
AA SpeedOutput speedyesterday#1249 tok/sbest of the picked#1954 tok/s
Price1
AA PriceBlended priceyesterday#10$1.50best of the picked#24$20.0
Usage1
OpenRouterWeekly tokensyesterday#132.2T tokbest of the picked#171.4T 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