PDEAgent-Bench
Models write finite element solvers for partial differential equations. A solver must run successfully, meet a numerical error tolerance, and finish within its time limit.
The authors rank five models and three agents across three solver libraries. The MUSE team separately evaluated its agent on 451 held-out cases.
- Made by
- PDEAgent-Bench team
- Released
- May 2026
- Kind
- Scientific code
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Code sandbox
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Gemini 3.1 Pro leads with 54.1% among models released by April 2026 Gemini 3.1 Pro leads with 54.1% among models released by April 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Every run is in the next chart. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as CodePDE + GPT-5.4, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 3.1 Pro DOLFINx 54.1%
- 2 Claude Opus 4.7 DOLFINx 47.8%
- 3 GPT-5.4 DOLFINx 46%
- 4 CodePDE + GPT-5.4 DOLFINx 44.7%
- 5 OpenHands + GPT-5.4 DOLFINx 43.6%
- 6
Qwen 3.6 Plus DOLFINx 23.4%
- 7
DeepSeek-V3.2 DOLFINx 4.20%
Source: Official PDEAgent-Bench leaderboard
- 1
Gemini 3.1 Pro DOLFINx 54.1%
- 2 Claude Opus 4.7 DOLFINx 47.8%
- 3 GPT-5.4 DOLFINx 46%
- 4
Qwen 3.6 Plus DOLFINx 23.4%
- 5
DeepSeek-V3.2 DOLFINx 4.20%
Source: Official PDEAgent-Bench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 54.1% | DOLFINx | Feb 2026 | Official leaderboard |
| 2 | Claude Opus 4.7 | 47.8% | DOLFINx | Apr 2026 | Official leaderboard |
| 3 | GPT-5.4 | 46% | DOLFINx | Mar 2026 | Official leaderboard |
| 4 | CodePDE + GPT-5.4 | 44.7% | DOLFINx | Mar 2026 | Official leaderboard |
| 5 | OpenHands + GPT-5.4 | 43.6% | DOLFINx | Mar 2026 | Official leaderboard |
| 6 | | 23.4% | DOLFINx | Mar 2026 | Official leaderboard |
| 7 | | 4.20% | DOLFINx | Dec 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 54.1% | DOLFINx | Feb 2026 | Official leaderboard |
| 2 | Claude Opus 4.7 | 47.8% | DOLFINx | Apr 2026 | Official leaderboard |
| 3 | GPT-5.4 | 46% | DOLFINx | Mar 2026 | Official leaderboard |
| 4 | | 23.4% | DOLFINx | Mar 2026 | Official leaderboard |
| 5 | | 4.20% | DOLFINx | Dec 2025 | Official leaderboard |
Rankings by part
We read 11 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Poisson, Helmholtz and Biharmonic. Gemini 3.1 Pro leads 7 of them, and Claude Opus 4.7 leads the other 4. Arrows show how far a model moved from its overall rank among the models we track.
Poisson
5 models we track have a score here.
- 1 Claude Opus 4.7 ↑1 54.9%
- 2
Gemini 3.1 Pro ↓1 51.6%
- 3 GPT-5.4 47.3%
- 4
Qwen 3.6 Plus 27.5%
- 5
DeepSeek-V3.2 14.3%
Helmholtz
5 models we track have a score here.
- 1
Gemini 3.1 Pro 71%
- 2 Claude Opus 4.7 62.9%
- 3 GPT-5.4 46.8%
- 4
Qwen 3.6 Plus 40.3%
- 5
DeepSeek-V3.2 0%
Biharmonic
5 models we track have a score here.
- 1
Gemini 3.1 Pro 100%
- 2 Claude Opus 4.7 93.3%
- 3 GPT-5.4 47.4%
- 4
Qwen 3.6 Plus 33.3%
- 5
DeepSeek-V3.2 8.80%
Linear Elasticity
5 models we track have a score here.
- 1
Gemini 3.1 Pro 66.7%
- 2 Claude Opus 4.7 66.7%
- 3 GPT-5.4 47.6%
- 4
Qwen 3.6 Plus 28.6%
- 5
DeepSeek-V3.2 3.20%
Heat
5 models we track have a score here.
- 1 Claude Opus 4.7 ↑1 76%
- 2
Gemini 3.1 Pro ↓1 58%
- 3 GPT-5.4 48%
- 4
Qwen 3.6 Plus 34%
- 5
DeepSeek-V3.2 10%
Convection–Diffusion
5 models we track have a score here.
- 1 Claude Opus 4.7 ↑1 58.3%
- 2
Gemini 3.1 Pro ↓1 52.4%
- 3 GPT-5.4 46.4%
- 4
Qwen 3.6 Plus 29.8%
- 5
DeepSeek-V3.2 2.40%
Reaction–Diffusion
5 models we track have a score here.
- 1
Gemini 3.1 Pro 64.1%
- 2 Claude Opus 4.7 51.6%
- 3 GPT-5.4 46.9%
- 4
Qwen 3.6 Plus 27.3%
- 5
DeepSeek-V3.2 0%
Stokes
5 models we track have a score here.
- 1
Gemini 3.1 Pro 51.9%
- 2 Claude Opus 4.7 44.4%
- 3 GPT-5.4 34.4%
- 4
Qwen 3.6 Plus 15.4%
- 5
DeepSeek-V3.2 1.60%
Navier–Stokes
5 models we track have a score here.
- 1 Claude Opus 4.7 ↑1 57.1%
- 2 GPT-5.4 ↑1 50%
- 3
Gemini 3.1 Pro ↓2 32.1%
- 4
Qwen 3.6 Plus 32.1%
- 5
DeepSeek-V3.2 0%
Burgers
5 models we track have a score here.
- 1
Gemini 3.1 Pro 53.5%
- 2 GPT-5.4 ↑1 46.5%
- 3 Claude Opus 4.7 ↓1 27.9%
- 4
Qwen 3.6 Plus 18.6%
- 5
DeepSeek-V3.2 0%
Wave
5 models we track have a score here.
- 1
Gemini 3.1 Pro 47.6%
- 2 GPT-5.4 ↑1 47.6%
- 3 Claude Opus 4.7 ↓1 28.6%
- 4
Qwen 3.6 Plus 21.4%
- 5
DeepSeek-V3.2 0%
The best score, 54.1%, costs $0.04 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official PDEAgent-Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| DOLFINx | 54.1% | $0.04 | |||
| Claude Opus 4.7 | DOLFINx | 47.8% | $0.09 | ||
| GPT-5.4 | DOLFINx | 46% | $0.06 | ||
| Claude Opus 4.7 | Firedrake | 45.9% | $0.09 | ||
| CodePDE + GPT-5.4 | DOLFINx | CodePDE | 44.7% | $0.06 | |
| OpenHands + GPT-5.4 | DOLFINx | OpenHands | 43.6% | $0.15 | |
| GPT-5.4 | Firedrake | 38% | $0.06 | ||
| Firedrake | 32.4% | $0.04 | |||
| deal.II | 32.3% | $0.04 | |||
| OpenHands + GPT-5.4 | Firedrake | OpenHands | 28.8% | $0.15 | |
| Claude Opus 4.7 | deal.II | 28.1% | $0.09 | ||
| CodePDE + GPT-5.4 | Firedrake | CodePDE | 25.3% | $0.06 | |
| CodePDE + GPT-5.4 | deal.II | CodePDE | 24.6% | $0.06 | |
| DOLFINx | 23.4% | $0.02 | |||
| Firedrake | 22.9% | $0.02 | |||
| GPT-5.4 | deal.II | 19.2% | $0.06 | ||
| deal.II | 16.9% | $0.02 | |||
| OpenHands + GPT-5.4 | deal.II | OpenHands | 16.6% | $0.15 | |
| GPT-5.4 | Firedrake | Mini-SWE-Agent | 12.9% | $0.07 | |
| DOLFINx | 4.20% | $0.003 | |||
| GPT-5.4 | DOLFINx | Mini-SWE-Agent | 3.70% | $0.07 | |
| Firedrake | 2.70% | $0.003 | |||
| deal.II | 0% | $0.003 | |||
| GPT-5.4 | deal.II | Mini-SWE-Agent | 0% | $0.07 |
The best score, 54.1%, costs $0.04 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official PDEAgent-Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| DOLFINx | 54.1% | $0.04 | |||
| Claude Opus 4.7 | DOLFINx | 47.8% | $0.09 | ||
| GPT-5.4 | DOLFINx | 46% | $0.06 | ||
| Claude Opus 4.7 | Firedrake | 45.9% | $0.09 | ||
| GPT-5.4 | Firedrake | 38% | $0.06 | ||
| Firedrake | 32.4% | $0.04 | |||
| deal.II | 32.3% | $0.04 | |||
| Claude Opus 4.7 | deal.II | 28.1% | $0.09 | ||
| DOLFINx | 23.4% | $0.02 | |||
| Firedrake | 22.9% | $0.02 | |||
| GPT-5.4 | deal.II | 19.2% | $0.06 | ||
| deal.II | 16.9% | $0.02 | |||
| GPT-5.4 | Firedrake | Mini-SWE-Agent | 12.9% | $0.07 | |
| DOLFINx | 4.20% | $0.003 | |||
| GPT-5.4 | DOLFINx | Mini-SWE-Agent | 3.70% | $0.07 | |
| Firedrake | 2.70% | $0.003 | |||
| deal.II | 0% | $0.003 | |||
| GPT-5.4 | deal.II | Mini-SWE-Agent | 0% | $0.07 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official PDEAgent-Bench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PDEAgent-Bench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8%
- Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance.
DeepSeek V4.1 Flash 3,471
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Claude Opus 4.7. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 5 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Claude Opus 4.7.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
- Pass Headroom The best is 54.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on zeroeclipse00.github.io: 24 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.