WorkBuddy Bench (Claude Code) - Office: leaderboard
Metric: Score (0-100) on the 50 office data and file workflow tasks scored by a task-specific blend of rule and evidence-grounded judge scores, run in the Claude Code harness in think mode, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 86.05 |
| 2 | Claude Opus 4.8 (Thinking) | 83.23 |
| 3 | Hy3 | 80.08 |
| 4 | GLM-5.2 | 79.57 |
| 5 | MiniMax-M3 | 76.3 |
Interactive version: theaggregate.ai/benchmark?slug=workbuddy-bench-claude-code-office · How It Works · Data refreshed daily, snapshot 2026-09-29.