PDEAgent-Bench - Stokes: leaderboard
PDEAgent-Bench (Hang et al., 2026) gives a model a structured PDE specification and asks for a complete finite-element solver in one attempt, with no execution feedback: the 61 Stokes flow problems with saddle-point structure of the primary DOLFINx 0.10 track. A case passes only if the solver runs, returns a valid solution within 10 times the calibration baseline's relative L2 error and finishes within 3 times its runtime; the score is the pass rate in percent, higher is better.
Metric: Case pass rate (%; 61 DOLFINx cases, single-shot, temperature 0). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 34.4 | #121 |
| 2 | Claude Opus 4.7 | 24.6 | #75 |
| 3 | Gemini 3.1 Pro (Preview) | 21.3 | #91 |
| 4 | Qwen 3.6 Plus | 6.6 | #217 |
| 5 | DeepSeek V3.2 | 1.6 | #403 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=pdeagent-bench-stokes · How It Works · Data refreshed daily, snapshot 2026-11-12.