Benchmark Almanac

PE Civil Bench

GPT-5.5 87.3% leads since April 2026
Not in model cards

Models solve 110 multiple-choice and 40 numerical civil engineering exam problems. A model compares each answer with the reference solution.

The authors compare 13 models on questions modeled on the Fundamentals of Engineering and Professional Engineering Civil exams.

Released
March 2026
Kind
Exam questions
Level
University
Scored
Graded by a model
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text, Actions
Interaction
Agentic
Environment
APIs and tools
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
Occupations
Architecture and engineering
In views
Agents
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
11
Entries in its paper, 8 models we track

GPT-5.5 leads with 87.3% among models released by April 2026 GPT-5.5 leads with 87.3% among models released by April 2026

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. 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:

  1. 1 GPT-5.5 Agentic RAG 87.3%
  2. 2 GPT-5.4 Agentic RAG 84.7%
  3. 3 Gemini 2.5 Pro (snapshot unspecified) Agentic RAG 78%
  4. 4 o4-mini Agentic RAG 72%
  5. 5 o3-mini Agentic RAG 71.3%
  6. 6 GPT-4o (snapshot unspecified) Agentic RAG 70.7%
  7. 7 Llama 3.1-405B Agentic RAG 60.7%
  8. 8 GPT-4o-mini (snapshot unspecified) Agentic RAG 52.7%
  9. 9 Llama 3.3 70B Agentic RAG 49.3%
  10. 10 Mistral 7B v0.1 Agentic RAG 32%
  11. 11 Llama 3.1-8B Agentic RAG 29.3%

Source: The PE Civil Bench paper

#EntryScoreSettingDateSource
1 GPT-5.5 87.3% Agentic RAG Apr 2026 Official leaderboard
2 GPT-5.4 84.7% Agentic RAG Mar 2026 Official leaderboard
3 Gemini 2.5 Pro (snapshot unspecified) 78% Agentic RAG Official leaderboard
4 o4-mini 72% Agentic RAG Apr 2025 Official leaderboard
5 o3-mini 71.3% Agentic RAG Jan 2025 Official leaderboard
6 GPT-4o (snapshot unspecified) 70.7% Agentic RAG Official leaderboard
7 Llama 3.1-405B 60.7% Agentic RAG Jul 2024 Official leaderboard
8 GPT-4o-mini (snapshot unspecified) 52.7% Agentic RAG Official leaderboard
9 Llama 3.3 70B 49.3% Agentic RAG Dec 2024 Official leaderboard
10 Mistral 7B v0.1 32% Agentic RAG Sep 2023 Official leaderboard
11 Llama 3.1-8B 29.3% Agentic RAG Jul 2024 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.5 87.3% Agentic RAG Apr 2026 Official leaderboard
2 GPT-5.4 84.7% Agentic RAG Mar 2026 Official leaderboard
3 o4-mini 72% Agentic RAG Apr 2025 Official leaderboard
4 o3-mini 71.3% Agentic RAG Jan 2025 Official leaderboard
5 Llama 3.1-405B 60.7% Agentic RAG Jul 2024 Official leaderboard
6 Llama 3.3 70B 49.3% Agentic RAG Dec 2024 Official leaderboard
7 Mistral 7B v0.1 32% Agentic RAG Sep 2023 Official leaderboard
8 Llama 3.1-8B 29.3% Agentic RAG Jul 2024 Official leaderboard

3 models have held number one in the benchmark’s paper since its release in March 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Benchmark paper Passed 85% in Apr 2026, by GPT-5.5
GPT-5.5 87.3%

Source: The PE Civil Bench paper

GPT-5.5 on the official leaderboard passed 85% in April 2026

That was 1 month after its release. By the same age, 20% of the benchmarks from 2026 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) GPT-5.5 o4-mini Llama 3.1-405B Mistral 7B v0.1 0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) GPT-5.5 o4-mini

Source: Official PE Civil 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

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 benchmark’s paper (11 entries).
  • Pass Models scored 8 models we track, plus 3 other entries on its leaderboard.
  • Note Newest score The newest came 7 months ago, in April 2026, for GPT-5.5. 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 GPT-5.5 (#21).
  • Note Headroom Saturated. The best is 87.3%, past 85% since April 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on komal-blkmmb.github.io: 8 rows for models we track and 3 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.

How we check