PLE Dev - Overall - dsh: leaderboard
PLE evaluates agents on its separate 29-task development set from professional engineering work. Results distinguish the agent tools and engineering discipline. Mean task reward (0–1).
Metric: Mean task reward (0–1). Source: ple-bench.com. 1 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek-V4.1-Flash | 0.17 |
Interactive version: theaggregate.ai/benchmark?slug=ple-dev-overall-dsh · How It Works · Data refreshed daily, snapshot 2026-10-29.