Llama 4 Maverick coding benchmark

How Llama 4 Maverick performed

Llama 4 Maverick by Meta took the PomBench AI coding benchmark: every model gets the same prompt and writes self-contained browser code for a twelve-second scene: a Pomeranian runs across a backyard, jumps a puddle, enters its doghouse, retrieves a bone and turns toward the viewer. The video above is an independent offline browser recording of the code Llama 4 Maverick returned, captured at 960 × 540 and 30 fps, with no organizer edits to the code.

In this Llama 4 Maverick coding test the model produced 763 output tokens, including provider-reported reasoning (rank 45 of 46 by output tokens), and the known API cost was $0.0013 (rank 4 of 45, cheapest first). Is Llama 4 Maverick good at coding? One task cannot answer that on its own, so this LLM coding benchmark lets you watch the result instead of reading a score: check the gait, the puddle jump and reflection, the doorway occlusion and whether the bone stays in the dog's mouth.

Then compare Llama 4 Maverick vs Llama 4 Scout and Muse Wonder below, or open the AI model comparison to play up to four models on one synchronized timeline.