Every AI leaderboard

28 leaderboards · 986 models ranked

Llama4 Maverick vs Claude Fable 5.1 vs Qwen3.8 Max (0902) vs DeepSeek V4P1 Flash

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

  • Llama4 Maverick
  • Claude Fable 5.1
  • Qwen3.8 Max (0902)
  • DeepSeek V4P1 Flash

Head to head on 9 boards: Claude Fable 5.1 places best on 5, Qwen3.8 Max (0902) places best on 4, Llama4 Maverick places best on 0 and DeepSeek V4P1 Flash places best on 0. All 4 ranked on 0 of 17 boards.

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

BoardLlama4 MaverickClaude Fable 5.1Qwen3.8 Max (0902)DeepSeek V4P1 Flash
Chat2
Text ArenaArena ratingyesterday#61,504best of the picked#201,483
MultiChallengeScoreyesterday#574.9%
Reasoning7
LiveBenchGlobal averageyesterday#183.4%best of the picked#1678.5%
Epoch ECIECIyesterday#5166.9best of the picked#27157.4
AA IntelligenceIndexyesterday#950.0best of the picked#1533.7
HLEAccuracyyesterday#246.5%
ARC-AGI-2Scoreyesterday#790.0%
GPQA DiamondAccuracyyesterday#2692.7%
MMLU-ProAccuracy · staleyesterday#5980.5%
Coding2
WebDev ArenaArena ratingyesterday#51,746best of the picked#121,677
SWE-Bench ProResolvedyesterday#292.2%
Agents and tools2
Search ArenaArena ratingyesterday#71,227#61,228best of the picked
MCP AtlasPass rateyesterday#387.2%
Vision2
Vision ArenaArena ratingyesterday#131,288#21,300best of the picked
Document ArenaArena ratingyesterday#21,499
Speed1
AA SpeedOutput speedyesterday#1422 tok/s#260 tok/sbest of the picked
Price1
AA PriceBlended priceyesterday#17$20.0#8$3.00best of the picked

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