PDEAgent-Bench - Convection-Diffusion: leaderboard
Metric: Case pass rate (%; 84 DOLFINx cases, single-shot, temperature 0). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 58.3 |
| 2 | Gemini 3.1 Pro (Preview) | 52.4 |
| 3 | GPT-5.4 | 46.4 |
| 4 | Qwen 3.6 Plus | 29.8 |
| 5 | DeepSeek V3.2 | 2.4 |
Interactive version: theaggregate.ai/benchmark?slug=pdeagent-bench-convection-diffusion · How It Works · Data refreshed daily, snapshot 2026-09-25.