GPT-6.1 Sol coding benchmark

How GPT-6.1 Sol performed

GPT-6.1 Sol by OpenAI 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 GPT-6.1 Sol returned, captured at 960 × 540 and 30 fps, with no organizer edits to the code.

In this GPT-6.1 Sol coding test the model produced 8,989 output tokens, including provider-reported reasoning (rank 19 of 46 by output tokens), and the known API cost was $0.0950 (rank 26 of 45, cheapest first). Is GPT-6.1 Sol 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 GPT-6.1 Sol vs GPT-6 Sol and Gemini 4 Argon below, or open the AI model comparison to play up to four models on one synchronized timeline.