Qwen3.5 35B-A3B
Qwen vision-language model for visual reasoning, documents, and agent tasks
ECI STANDING#92 of 266
SCORE142.53140.39–144.77 CI
FRONTIER LAGLaunched 10.8 months behindScores about what Gemini 2.5 Pro (Mar 2025) did in March 2025.
SCORES LIKE THESE MODELSGemma 4 31B ITGoogle DeepMind · Apr 2026142.66GPT-5.5 InstantOpenAI · May 2026142.5
Full Epoch Capabilities Index ranking ↗Gemini 2.5 Pro (May 2025)Google DeepMind · May 2025142.47
Qwen3-MaxAlibaba · Sep 2025142.43RELEASE DATEFeb 23, 2026
WEIGHTSOpen weights
CONTEXT WINDOW262.1K
MAX OUTPUT65.5K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image, video, audio
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.