Multimodal & Grounded benchmark
Flame-VLM-Code leaderboard
Every model the catalog carries a published Flame-VLM-Code value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureVision-language code generation
TasksMultimodal coding tasks
DifficultyMultimodal coding
Published byGLM-5V-Turbo
A vision-language coding benchmark for generating correct code from visual and multimodal inputs.
No model in the catalog has a published Flame-VLM-Code score.
The benchmark is defined by GLM-5V-Turbo, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.