Benchmark Almanac

SemaPLC Function Track

GPT-5.5 82.1% leads since August 2026
Not in model cards

Agents generate individual Structured Text program units. A compiler and a formal verifier check the program against the requirements. Inconclusive checks count as failures.

Engineers revised 53 of 117 Agents4PLC tasks. The resulting set has 607 verification properties. The public download includes the original and revised data.

Released
August 2026
Kind
Electronics
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
June 2026
Scores refreshed
November 20th, 2026
7
Models scored in its paper

GPT-5.5 leads with 82.1% among models released by June 2026

Best score per model 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. Every run is in the next chart.

The newest model with a score here came out in June 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 full 82.1%
  2. 2 GLM-5.2 full 76.1%
  3. 3 Qwen3.5-Plus full 75.2%
  4. 4 MiniMax-M2.7 full 69.2%
  5. 5 DeepSeek-V4-Pro full 69.2%
  6. 6 MiniMax-M3 full 69.2%
  7. 7 DeepSeek-V4-Flash full 67.5%

Source: The SemaPLC Function Track paper

#ModelScoreSettingDateSource
1 GPT-5.5 82.1% full, SemaPLC Apr 2026 Official leaderboard
2 GLM-5.2 76.1% full, SemaPLC Jun 2026 Official leaderboard
3 Qwen3.5-Plus 75.2% full, SemaPLC Feb 2026 Official leaderboard
4 MiniMax-M2.7 69.2% full, SemaPLC Mar 2026 Official leaderboard
5 DeepSeek-V4-Pro 69.2% full, SemaPLC Apr 2026 Official leaderboard
6 MiniMax-M3 69.2% full, SemaPLC Jun 2026 Official leaderboard
7 DeepSeek-V4-Flash 67.5% full, SemaPLC Apr 2026 Official leaderboard

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-5.5 SemaPLC
bare full
82.1%
GLM-5.2 SemaPLC
bare full
76.1%
Qwen3.5-Plus SemaPLC
bare full
75.2%
MiniMax-M2.7 SemaPLC
bare full
69.2%
DeepSeek-V4-Pro SemaPLC
bare full
69.2%
MiniMax-M3 SemaPLC
bare full
69.2%
DeepSeek-V4-Flash SemaPLC
bare full
67.5%

Source: The SemaPLC Function Track paper

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.5 full SemaPLC 82.1%
GPT-5.5 AutoPLC 79.5%
GPT-5.5 Agents4PLC 78.6%
GLM-5.2 full SemaPLC 76.1%
Qwen3.5-Plus full SemaPLC 75.2%
GLM-5.2 Agents4PLC 74.4%
GPT-5.5 bare SemaPLC 71.8%
MiniMax-M2.7 full SemaPLC 69.2%
DeepSeek-V4-Pro full SemaPLC 69.2%
MiniMax-M3 full SemaPLC 69.2%
Qwen3.5-Plus AutoPLC 67.5%
Qwen3.5-Plus Agents4PLC 67.5%
DeepSeek-V4-Flash full SemaPLC 67.5%
MiniMax-M3 AutoPLC 65%
GLM-5.2 bare SemaPLC 63.2%
Qwen3.5-Plus bare SemaPLC 62.4%
DeepSeek-V4-Pro Agents4PLC 62.4%
DeepSeek-V4-Pro AutoPLC 61.5%
MiniMax-M3 bare SemaPLC 60.7%
GLM-5.2 AutoPLC 59%
DeepSeek-V4-Pro bare SemaPLC 55.6%
MiniMax-M3 Agents4PLC 55.6%
DeepSeek-V4-Flash AutoPLC 54.7%
DeepSeek-V4-Flash Agents4PLC 54.7%
MiniMax-M2.7 Agents4PLC 53.8%
MiniMax-M2.7 AutoPLC 49.6%
GPT-5.5 LLM4PLC 44.4%
DeepSeek-V4-Pro LLM4PLC 43.6%
DeepSeek-V4-Flash LLM4PLC 41%
MiniMax-M2.7 bare SemaPLC 39.3%
DeepSeek-V4-Flash bare SemaPLC 34.2%
GLM-5.2 LLM4PLC 30.8%
MiniMax-M2.7 LLM4PLC 22.2%
MiniMax-M3 LLM4PLC 15.4%
Qwen3.5-Plus LLM4PLC 13.7%

Number one over time

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

OpenAI
Benchmark paper Not tested since Aug 2026
GPT-5.5 82.1%

Source: The SemaPLC Function Track paper

Scores over time

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% 2026 Near the ceiling (85%) GPT-5.5 Qwen3.5-Plus 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 Qwen3.5-Plus

Source: Official SemaPLC Function Track 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 Engineering and CAD

All 112 in Engineering and CAD
  • EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge. Gemini 4 Carbon 83.9%
  • 3DCodeBench In use Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity. LongCat-2.5 55.4%
  • CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
  • PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%
  • Razavi-Bench Not in model cards Models explain what happens in analog circuits and why. A language model awards up to four points per answer against a reference and a rubric. Gemini 4 Carbon 98.3%
  • CircuitRubric Not in model cards Models write analog circuit netlists from design requests. A program compares transistor connections and relative device sizes with accepted reference circuits. Claude Opus 4.8 96%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (7 entries).
  • Pass Models scored 7 models we track.
  • Pass Newest score The newest is from June 2026, for GLM-5.2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 82.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 35 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.

How we check