Compare models

• Alibaba

Add a lab

Add:OpenAIAnthropicGoogleMicrosoft

Alibaba is ranked on 25 boards. Add another to compare.

Board	Read	Alibaba
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday	#201,483Qwen3.8 Max (0902)
MultiChallengeScoretodaytoday	Nov 9todaytoday	#3341.2%Qwen3-235B-A22B-Thinking (Jul 2025)
Reasoning6
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#787.8%Qwen3.5 397B A17B
AA IntelligenceIndextodaytoday	Nov 9todaytoday	#1533.7Qwen3.8 Max (0902)
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday	#1678.5%Qwen3.8 Max (0902)
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#2692.7%Qwen3.8 Max (0902)
Epoch ECIECItodaytoday	Nov 9todaytoday	#27157.4Qwen3.8 Max (0902)
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#4342.4%Qwen3.8 27B
Coding3
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday	#121,677Qwen3.8 Max (0902)
Aider PolyglotPass rate · staletodaytoday	Nov 9todaytoday	#1859.6%Qwen3 235b A22B Diff No Alibaba
SWE-bench VerifiedResolved · staletodaytoday	Nov 9todaytoday	#2355.4%Qwen3-Coder 480B/A35B Instruct
Agents and tools3
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#61,228Qwen3.8 Max (0902)
MCP AtlasPass ratetodaytoday	Nov 9todaytoday	#784.5%Qwen3.8 2.4T A95B
BFCLOverall accuracy · staletodaytoday	Nov 9todaytoday	#2052.1%Qwen3-235B-A22B-Thinking (Jul 2025)
Vision2
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday	#21,300Qwen3.8 Max (0902)
Document ArenaArena ratingtodaytoday	Nov 9todaytoday	#311,446Qwen3.7 Plus
Image2
Text-to-ImageArena ratingtodaytoday	Nov 9todaytoday	#131,254Qwen Image 3.0 Pro
Image EditArena ratingtodaytoday	Nov 9todaytoday	#201,364Qwen Image 2.1
Video2
Image-to-VideoArena ratingtodaytoday	Nov 9todaytoday	#51,481Wan 3.0
Text-to-VideoArena ratingtodaytoday	Nov 9todaytoday	#81,477Wan 3.0
Speech2
Speech ArenaArena ratingtodaytoday	Nov 9todaytoday	#31,303Qwen Audio 3.1 TTS Plus
Open ASRAverage WERtodaytoday	Nov 9todaytoday	#106.15 WERQwen3-ASR-1.7B-hf (Qwen)
Embeddings1
MTEBMean task scoretodaytoday	Nov 9todaytoday	#470.6%Qwen3-Embedding-8B (Qwen)
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday	#260 tok/sQwen3.8 Max (0902)
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday	#8$3.00Qwen3.8 Max (0902)

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.