LLM-CAE-Benchmark
Models generate Gmsh geometry and Elmer solver files for a square bar and a wheel and axle assembly. The authors score each output separately.
The authors publish four tables for nine models. Solver input quality and simulated displacement are separate measures.
- Made by
- University of Birmingham
- Released
- June 2025
- Kind
- Scientific code
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- A simulator
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Llama 3-70B #182 on the capability index
- Last model added
- April 2024
- Scores refreshed
- November 20th, 2026
GPT-4o (snapshot unspecified) tops the leaderboard with 95% Llama 3-70B leads with 90% among models released by April 2024
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Llama 3-70B, at 90%. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2024, 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 GPT-4o (snapshot unspecified) 95%
- 2 GPT-4 (snapshot unspecified) 90%
- 3
Llama 3-70B 90%
- 4
Mixtral 8x22B 87.5%
- 5 GPT-3.5 (snapshot unspecified) 86.3%
- 6
Mixtral 8x7B 82.5%
- 7
Llama 3-8B 64.5%
- 8 PHI-3 Mini 43.3%
- 9
Llama 2-70B 18.3%
Source: Official LLM-CAE-Benchmark leaderboard
- 1
Llama 3-70B 90%
- 2
Mixtral 8x22B 87.5%
- 3
Mixtral 8x7B 82.5%
- 4
Llama 3-8B 64.5%
- 5
Llama 2-70B 18.3%
Source: Official LLM-CAE-Benchmark leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o (snapshot unspecified) | 95% | Official leaderboard | ||
| 2 | GPT-4 (snapshot unspecified) | 90% | Official leaderboard | ||
| 3 | | 90% | Apr 2024 | Official leaderboard | |
| 4 | | 87.5% | Apr 2024 | Official leaderboard | |
| 5 | GPT-3.5 (snapshot unspecified) | 86.3% | Official leaderboard | ||
| 6 | | 82.5% | Dec 2023 | Official leaderboard | |
| 7 | | 64.5% | Apr 2024 | Official leaderboard | |
| 8 | PHI-3 Mini | 43.3% | Official leaderboard | ||
| 9 | | 18.3% | Jul 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 90% | Apr 2024 | Official leaderboard | |
| 2 | | 87.5% | Apr 2024 | Official leaderboard | |
| 3 | | 82.5% | Dec 2023 | Official leaderboard | |
| 4 | | 64.5% | Apr 2024 | Official leaderboard | |
| 5 | | 18.3% | Jul 2023 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Square Bar Geometry, Wheel & Axle Assembly and Square Bar Simulation. Mixtral 8x7B leads 3 of them, and Mixtral 8x22B leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Square Bar Geometry
5 models we track have a score here.
- 1
Mixtral 8x22B ↑1 100%
- 2
Llama 3-70B ↓1 100%
- 3
Mixtral 8x7B 60%
- 4
Llama 3-8B 40%
- 5
Llama 2-70B 23%
Wheel & Axle Assembly
5 models we track have a score here.
- 1
Mixtral 8x7B ↑2 70%
- 2
Llama 3-70B ↓1 60%
- 3
Mixtral 8x22B ↓1 50%
- 4
Llama 2-70B ↑1 35%
- 5
Llama 3-8B ↓1 35%
Square Bar Simulation
5 models we track have a score here.
- 1
Mixtral 8x7B ↑2 100%
- 2
Mixtral 8x22B 100%
- 3
Llama 3-70B ↓2 100%
- 4
Llama 3-8B 100%
- 5
Llama 2-70B 5.00%
Wheel & Axle Simulation
5 models we track have a score here.
- 1
Mixtral 8x7B ↑2 100%
- 2
Mixtral 8x22B 100%
- 3
Llama 3-70B ↓2 100%
- 4
Llama 3-8B 83%
- 5
Llama 2-70B 10%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LLM-CAE-Benchmark leaderboard
Mixtral 8x22B on the official leaderboard passed 85% in April 2024
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official LLM-CAE-Benchmark 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 5 models we track, plus 4 other entries on its leaderboard.
- Note Newest score The newest came 2 years ago, in April 2024, for Llama 3-70B. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Llama 3-70B (#182).
- Note Headroom Saturated. The best is 90%, past 85% since April 2024.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 5 rows for models we track and 4 other entries 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.