DeepSeek V4.1 Flash coding benchmark

How DeepSeek V4.1 Flash performed

DeepSeek V4.1 Flash by DeepSeek 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 DeepSeek V4.1 Flash returned, captured at 960 × 540 and 30 fps, with no organizer edits to the code.

In this DeepSeek V4.1 Flash coding test the model produced 8,357 output tokens, including provider-reported reasoning (rank 23 of 46 by output tokens), and the known API cost was $0.0106 (rank 12 of 45, cheapest first). Is DeepSeek V4.1 Flash 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 DeepSeek V4.1 Flash vs DeepSeek V4 Pro and GPT-6 Astra below, or open the AI model comparison to play up to four models on one synchronized timeline.