Every AI leaderboard

28 leaderboards · 986 models ranked

Claude Opus 4.6 vs Qwen3.8 Max (0902)

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

  • Claude Opus 4.6
  • Qwen3.8 Max (0902)

Head to head on 7 boards: Qwen3.8 Max (0902) places best on 6 and Claude Opus 4.6 places best on 1. Both ranked on 7 of 17 boards.

BoardClaude Opus 4.6Qwen3.8 Max (0902)
Chat2
Text ArenaArena ratingtoday#71,503best of the picked#201,483
MultiChallengeScoretoday#2356.0%
Reasoning7
LiveBenchGlobal averagetoday#3974.5%#1678.5%best of the picked
GPQA DiamondAccuracytoday#4090.5%#2692.7%best of the picked
Epoch ECIECItoday#33156.3#27157.4best of the picked
MMLU-ProAccuracy · staletoday#489.1%
HLEAccuracytoday#1134.4%
AA IntelligenceIndextoday#1533.7
ARC-AGI-2Scoretoday#2669.2%
Coding2
WebDev ArenaArena ratingtoday#431,546#121,677best of the picked
SWE-bench VerifiedResolved · staletoday#475.6%
Agents and tools2
Search ArenaArena ratingtoday#91,222#61,228best of the picked
MCP AtlasPass ratetoday#1976.8%
Vision2
Vision ArenaArena ratingtoday#41,299#21,300best of the picked
Document ArenaArena ratingtoday#31,496
Speed1
AA SpeedOutput speedtoday#260 tok/s
Price1
AA PriceBlended pricetoday#8$3.00

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