PostEDA-Bench (Proposer-Critic) - PPA-Mono: leaderboard
Metric: Success rate (%; 35 single-objective PPA tasks, mean of 5 temperature-0 runs per task, Proposer-Critic agent). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 42.85 |
| 2 | Gemma 4 31B (IT) | 42.28 |
| 3 | Qwen 3.5 122B A10B | 39.99 |
| 4 | Qwen 3.5 9B | 3.99 |
Interactive version: theaggregate.ai/benchmark?slug=posteda-bench-proposer-critic-ppa-mono · How It Works · Data refreshed daily, snapshot 2026-09-25.