HWE-Bench (Codex CLI): leaderboard
HWE-bench (PKU) run with the Codex CLI agent: 417 simulation-verified RTL bug-repair cases across six open hardware projects; percent of cases resolved.
Metric: Resolved (%). Source: pku-liang.github.io. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 79.9 | #22 (GPT-5.6 Sol) |
| 2 | GPT-5.5 (xHigh) | 76.5 | #33 (GPT-5.5) |
| 3 | GPT-5.4 (xHigh) | 70.7 | #83 (GPT-5.4) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=hwe-bench-codex-cli · How It Works · Data refreshed daily, snapshot 2026-11-05.