PDEAgent-Bench: 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. This is the primary DOLFINx 0.10 track: 645 cases over 11 PDE families (elliptic, parabolic, hyperbolic, incompressible-flow, reaction-diffusion and elasticity problems) on 14 domain shapes. 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 (%; 645 DOLFINx cases, single-shot, temperature 0; a case passes when the solver executes, stays within 10x the calibration error and 3x the calibration runtime). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 54.1 | #91 |
| 2 | Claude Opus 4.7 | 47.8 | #75 |
| 3 | GPT-5.4 | 46 | #121 |
| 4 | Qwen 3.6 Plus | 23.4 | #217 |
| 5 | DeepSeek V3.2 | 4.2 | #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 · How It Works · Data refreshed daily, snapshot 2026-11-12.