Every AI leaderboard

Leaderboards28Models ranked986

28 leaderboards · 986 models ranked

Kimi K2.5 vs Gemini 4 Argon vs Qwen3.8 Max (0902) vs GPT-6 Astra

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

  • Kimi K2.5
  • Gemini 4 Argon
  • Qwen3.8 Max (0902)
  • GPT-6 Astra

Head to head on 15 boards: GPT-6 Astra places best on 8, Gemini 4 Argon places best on 4, Qwen3.8 Max (0902) places best on 3 and Kimi K2.5 places best on 0. All 4 ranked on 3 of 17 boards.

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

BoardKimi K2.5Gemini 4 ArgonQwen3.8 Max (0902)GPT-6 Astra
Chat2
Text ArenaArena ratingtoday#681,450#21,523best of the picked#201,483#311,475
MultiChallengeScoretoday#1561.4%#278.7%best of the picked
Reasoning6
Epoch ECIECItoday#68148.7#6166.4#27157.4#1169.1best of the picked
GPQA DiamondAccuracytoday#196.4%best of the picked#2692.7%#295.8%
ARC-AGI-2Scoretoday#5611.8%#591.3%#195.0%best of the picked
AA IntelligenceIndextoday#750.4#1533.7#356.9best of the picked
HLEAccuracytoday#1724.4%#154.8%best of the picked
LiveBenchGlobal averagetoday#1678.5%#482.2%best of the picked
Coding3
WebDev ArenaArena ratingtoday#721,436#101,683#121,677#31,770best of the picked
SWE-Bench ProResolvedtoday#392.2%best of the picked#490.2%
SWE-bench VerifiedResolved · staletoday#1070.8%
Agents and tools2
Search ArenaArena ratingtoday#61,228#31,245best of the picked
MCP AtlasPass ratetoday#190.7%
Vision2
Vision ArenaArena ratingtoday#431,252#21,300best of the picked#171,285
Document ArenaArena ratingtoday#341,437#111,477best of the picked
Speed1
AA SpeedOutput speedtoday#1028 tok/s#260 tok/sbest of the picked#1621 tok/s
Price1
AA PriceBlended pricetoday#13$8.00#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