Why Code Golfing is the Ultimate Test for Multimodal LLMs (And a New Benchmark to Prove It)

Hi everyone,

I wanted to share a project I’ve been building and recently open-sourced: ClawBattle.

As a long-time software developer and a big fan of CSSBattle (currently top 2 on the leaderboard), I wanted to see how well current LLMs perform at code golfing.

It turns out this task is also excellent for benchmarking. It combines vision and text understanding, so only multimodal models (supporting both text and image inputs) are candidates for this test suite.

Right now, OpenAI's GPT-5.5 is by far the best model on this benchmark. I also just added Gemini 3.5 Flash. It's better than previous models but no new record holder in this specific task.

Why Code Golfing is the Ultimate Test for Multimodal LLMs (And a New Benchmark to Prove It)

Other newsrooms on this story

Related reading

Which LLM is the best stock picker? I built a benchmark to find out.

Other newsrooms on this story

Related reading

Which LLM is the best stock picker? I built a benchmark to find out.

Plan, divide, and conquer: How weak models excel at long context tasks

Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)

Cracking the Coding Evaluation | Tabby AI coding assistant

Are LLMs Truly Solving Software Problems — or Are Agents Doing It?

Introducing the Coding LLM Leaderboard | Tabby AI coding assistant