Tencent Visionary Flow
NEW HOTTencent · Qwen
API
Tencent's advanced image generation model, optimized for rich, culturally resonant visuals and high-quality animation frames.
VisionVideoLocalization
Scores 76% on MMLU, competitive across 4 standard benchmarks.
Data aggregated and editorially reviewed by TrendMing.
Benchmark Performance
MMLU76%
HumanEval57%
MATH51%
GPQA68%
Scores sourced from published evaluations. Higher = better.
Quick Specs
Context WindowN/A (Image tokens)
Parameters70B
Input pricing$0.003 / 1K images
Output pricing$0.006 / 1K images
Released2026-01-15