Qwen3 Max

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

ECI STANDING#95 of 266
SCORE142.43140.4–144.98 CI
FRONTIER LAGLaunched 5.8 months behindScores about what Gemini 2.5 Pro (Mar 2025) did in March 2025.
SCORES LIKE THESE MODELSQwen3.5-35B-A3BAlibaba · Feb 2026142.53GPT-5.5 InstantOpenAI · May 2026142.5
Gemini 2.5 Pro (May 2025)Google DeepMind · May 2025142.47
Claude Haiku 4.5Anthropic · Oct 2025142.37
Full Epoch Capabilities Index ranking
RELEASE DATESep 23, 2025
WEIGHTSClosed weights
CONTEXT WINDOW262.1K
MAX OUTPUT65.5K
REASONINGNo
TOOL CALLINGYes
INPUTStext
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.