WorkBuddy Bench (CodeBuddy Code) - Web: leaderboard

Metric: Score (0-100) on the 70 front-end and GUI tasks scored by rule, LLM or VLM and agent rubrics, run in the CodeBuddy Code harness in think mode, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 7 models tracked.

Top models

#ModelScore
1CodeBuddy Code + Claude Opus 4.8 (Thinking)68.14
2CodeBuddy Code + Hy367.71
3CodeBuddy Code + GLM-5.267.43
4CodeBuddy Code + GPT-5.561.14
5CodeBuddy Code + MiniMax-M358
6CodeBuddy Code + DeepSeek-V4-Pro (Thinking)54.57
7CodeBuddy Code + DeepSeek-V4-Flash (Thinking)47.29

Interactive version: theaggregate.ai/benchmark?slug=workbuddy-bench-codebuddy-code-web · How It Works · Data refreshed daily, snapshot 2026-09-29.