Qwen 3.5 Flash (hosted 35B-A3B) vs GPT-6 Astra vs Inkling Small 2 vs DeepSeek V4P1 Flash

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

Qwen 3.5 Flash (hosted 35B-A3B)
GPT-6 Astra
Inkling Small 2
DeepSeek V4P1 Flash

Head to head on 3 boards: GPT-6 Astra places best on 3, Qwen 3.5 Flash (hosted 35B-A3B) places best on 0, Inkling Small 2 places best on 0 and DeepSeek V4P1 Flash 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.

Board	Read	Qwen 3.5 Flash (hosted 35B-A3B)	GPT-6 Astra	Inkling Small 2	DeepSeek V4P1 Flash
Chat2
MultiChallengeScoreyesterday	Nov 9yesterday				#574.9%
Text ArenaArena ratingyesterday	Nov 9yesterday		#311,475
Reasoning6
Epoch ECIECIyesterday	Nov 9yesterday	#94143.8	#1169.1best of the picked
GPQA DiamondAccuracyyesterday	Nov 9yesterday	#8682.3%	#295.8%best of the picked
HLEAccuracyyesterday	Nov 9yesterday		#154.8%
ARC-AGI-2Scoreyesterday	Nov 9yesterday		#195.0%
AA IntelligenceIndexyesterday	Nov 9yesterday		#356.9
LiveBenchGlobal averageyesterday	Nov 9yesterday		#482.2%
Coding2
SWE-Bench ProResolvedyesterday	Nov 9yesterday		#490.2%best of the picked	#986.3%
WebDev ArenaArena ratingyesterday	Nov 9yesterday		#31,770
Agents and tools2
Search ArenaArena ratingyesterday	Nov 9yesterday		#31,245
MCP AtlasPass rateyesterday	Nov 9yesterday			#585.4%
Vision2
Document ArenaArena ratingyesterday	Nov 9yesterday		#111,477
Vision ArenaArena ratingyesterday	Nov 9yesterday		#171,285
Speed1
AA SpeedOutput speedyesterday	Nov 9yesterday		#1621 tok/s
Price1
AA PriceBlended priceyesterday	Nov 9yesterday		#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