Qwen3.7 Flash
Lightweight multimodal Qwen model for high-throughput text, image, and video tasks
ECI STANDING#79 of 266
SCORE144.63142.86–147.57 CI
FRONTIER LAGLaunched 15.3 months behindScores about what o3 did in April 2025.
SCORES LIKE THESE MODELS
Full Epoch Capabilities Index ranking ↗DeepSeek-V3.2-ExpDeepSeek · Sep 2025145.02
Gemini 3.1 Flash-LiteGoogle · Mar 2026144.49Grok 4 FastxAI · Sep 2025144.21
Gemini 2.5 Pro (Mar 2025)Google DeepMind · Mar 2025144.16
RELEASE DATEJul 15, 2026
WEIGHTSClosed weights
CONTEXT WINDOW1M
MAX OUTPUT65.5K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image, video
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.