Benchmark Almanac

PDAGENT-BENCH

GPT-5.5 65.1% leads since June 2026
Not in model cards

Models answer chip design questions, diagnose failures, interpret reports, and write tool commands. Rules grade five categories and model judges grade three.

The authors rank 16 models on 343 questions across two rounds with different judges. Three models have scores for six of the eight categories.

Made by
Qiufeng Li and colleagues
Released
June 2026
Kind
Electronics
Level
Expert
Scored
Checked automatically
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text, Code → Text, Code
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
16
Entries on its own leaderboard, 12 models we track

GPT-5.5 leads with 65.1% among models released by September 2026 GPT-5.5 leads with 65.1% among models released by September 2026

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. This view shows only models we track, each at its best.

The newest model with a score here came out in September 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 r1, 8 categories 65.1%
  2. 2 GPT-5.6 Sol r2, 8 categories 63.4%
  3. 3 Claude Opus 5 r2, 8 categories 60.5%
  4. 4 Claude Opus 4.7 r1, 8 categories 59.9%
  5. 5 DeepSeek V4.1 Flash r2, 8 categories 57.6%
  6. 6 Claude Sonnet 4.6 r1, 8 categories 57.3%
  7. 7 GPT-5.6 Luna r2, 8 categories 55.3%
  8. 8 Claude Sonnet 5 r2, 8 categories 51.5%
  9. 9 GPT-5.4 Mini r1, 8 categories 50.2%
  10. 10 GPT-5.1 r1, 8 categories 50.2%
  11. 11 DeepSeek-Reasoner r1, 6 categories 42.5%
  12. 12 DeepSeek-Chat r1, 6 categories 42%
  13. 13 GPT-5 mini r1, 8 categories 41%
  14. 14 Qwen-VL-30B r1, 8 categories 31.4%
  15. 15 Qwen-VL-8B r1, 8 categories 27.7%
  16. 16 Qwen3-8B r1, 6 categories 21.2%

Source: Official PDAGENT-BENCH leaderboard

#EntryScoreSettingDateSource
1 GPT-5.5 65.1% r1, 8 categories Apr 2026 Official leaderboard
2 GPT-5.6 Sol 63.4% r2, 8 categories Jul 2026 Official leaderboard
3 Claude Opus 5 60.5% r2, 8 categories Jul 2026 Official leaderboard
4 Claude Opus 4.7 59.9% r1, 8 categories Apr 2026 Official leaderboard
5 DeepSeek V4.1 Flash 57.6% r2, 8 categories Sep 2026 Official leaderboard
6 Claude Sonnet 4.6 57.3% r1, 8 categories Feb 2026 Official leaderboard
7 GPT-5.6 Luna 55.3% r2, 8 categories Jul 2026 Official leaderboard
8 Claude Sonnet 5 51.5% r2, 8 categories Jun 2026 Official leaderboard
9 GPT-5.4 Mini 50.2% r1, 8 categories Mar 2026 Official leaderboard
10 GPT-5.1 50.2% r1, 8 categories Nov 2025 Official leaderboard
11 DeepSeek-Reasoner open weights 42.5% r1, 6 categories Official leaderboard
12 DeepSeek-Chat open weights 42% r1, 6 categories Official leaderboard
13 GPT-5 mini 41% r1, 8 categories Aug 2025 Official leaderboard
14 Qwen-VL-30B open weights 31.4% r1, 8 categories Official leaderboard
15 Qwen-VL-8B open weights 27.7% r1, 8 categories Official leaderboard
16 Qwen3-8B 21.2% r1, 6 categories Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.5 65.1% r1, 8 categories Apr 2026 Official leaderboard
2 GPT-5.6 Sol 63.4% r2, 8 categories Jul 2026 Official leaderboard
3 Claude Opus 5 60.5% r2, 8 categories Jul 2026 Official leaderboard
4 Claude Opus 4.7 59.9% r1, 8 categories Apr 2026 Official leaderboard
5 DeepSeek V4.1 Flash 57.6% r2, 8 categories Sep 2026 Official leaderboard
6 Claude Sonnet 4.6 57.3% r1, 8 categories Feb 2026 Official leaderboard
7 GPT-5.6 Luna 55.3% r2, 8 categories Jul 2026 Official leaderboard
8 Claude Sonnet 5 51.5% r2, 8 categories Jun 2026 Official leaderboard
9 GPT-5.4 Mini 50.2% r1, 8 categories Mar 2026 Official leaderboard
10 GPT-5.1 50.2% r1, 8 categories Nov 2025 Official leaderboard
11 GPT-5 mini 41% r1, 8 categories Aug 2025 Official leaderboard
12 Qwen3-8B 21.2% r1, 6 categories Apr 2025 Official leaderboard

Rankings by part

We read 23 parts from the benchmark’s own leaderboard in 2 groups: understanding and script generation. Each ranks models on one part of the test. GPT-5.5 leads 8 of them, and 7 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Foundational Knowledge pass@1

12 models we track have a score here.

  1. 1 Claude Opus 5 ↑2 90%
  2. 2 GPT-5.6 Sol 85.7%
  3. 3 GPT-5.6 Luna ↑4 84.8%
  4. 4 DeepSeek V4.1 Flash ↑1 84.8%
  5. 5 Claude Sonnet 5 ↑3 82.9%
  6. 6 Claude Sonnet 4.6 82.6%
  7. 7 Claude Opus 4.7 ↓3 82.4%
  8. 8 GPT-5.1 ↑2 82%
  9. 9 GPT-5.5 ↓8 80.4%
  10. 10 GPT-5 mini ↑1 80%

Number one over time

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

OpenAI
Own leaderboard Not tested since Sep 2026
GPT-5.5 65.1%

Source: Official PDAGENT-BENCH leaderboard

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
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GPT-5.5 Claude Opus 4.7 GPT-5.1 GPT-5 mini Qwen3-8B 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GPT-5.5 Claude Sonnet 4.6

Source: Official PDAGENT-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 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 Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (16 entries).
  • Pass Models scored 12 models we track, plus 4 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for DeepSeek V4.1 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
  • Pass Headroom The best is 65.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on fenggev56.github.io: 12 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.

How we check