Every AI leaderboard

28 leaderboards · 986 models ranked

Kimi K2 Thinking vs GPT-6 Astra vs Qwen3.8 Max (0902) vs Claude Fable 5.1

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

  • Kimi K2 Thinking
  • GPT-6 Astra
  • Qwen3.8 Max (0902)
  • Claude Fable 5.1

Head to head on 14 boards: GPT-6 Astra places best on 7, Claude Fable 5.1 places best on 4, Qwen3.8 Max (0902) places best on 3 and Kimi K2 Thinking places best on 0. All 4 ranked on 1 of 19 boards.

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

BoardKimi K2 ThinkingGPT-6 AstraQwen3.8 Max (0902)Claude Fable 5.1
Chat2
Text ArenaArena ratingtoday#311,475#201,483#61,504best of the picked
MultiChallengeScoretoday#2455.4%
Reasoning7
Epoch ECIECItoday#85145.5#1169.1best of the picked#27157.4#5166.9
LiveBenchGlobal averagetoday#482.2%#1678.5%#183.4%best of the picked
AA IntelligenceIndextoday#356.9best of the picked#1533.7#950.0
HLEAccuracytoday#154.8%best of the picked#246.5%
ARC-AGI-2Scoretoday#195.0%best of the picked#790.0%
GPQA DiamondAccuracytoday#295.8%best of the picked#2692.7%
MMLU-ProAccuracy · staletoday#5681.0%
Coding4
WebDev ArenaArena ratingtoday#31,770best of the picked#121,677#51,746
SWE-Bench ProResolvedtoday#490.2%#292.2%best of the picked
SWE-bench VerifiedResolved · staletoday#1863.4%
Aider PolyglotPass rate · staletoday#1959.1%
Agents and tools2
Search ArenaArena ratingtoday#31,245best of the picked#61,228#71,227
MCP AtlasPass ratetoday#387.2%
Vision2
Vision ArenaArena ratingtoday#171,285#21,300best of the picked#131,288
Document ArenaArena ratingtoday#111,477#21,499best of the picked
Speed1
AA SpeedOutput speedtoday#1621 tok/s#260 tok/sbest of the picked#1422 tok/s
Price1
AA PriceBlended pricetoday#17$20.0#8$3.00best of the picked#17$20.0

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