Benchmark Almanac

Cua-Bench EDA (KiCad v1)

GPT-5.5 24% leads since June 2026
Not in model cards

Agents build or edit KiCad schematics through the desktop interface. The grader checks the resulting netlist and reports full passes, partial passes, and mean reward.

Snorkel AI and Cua AI report results for ten models on 25 schematic tasks.

Made by
Snorkel AI and Cua AI
Released
June 2026
Kind
Electronics
Level
Expert
Scored
Checked automatically
Answers
Agent task
Measures
Capability
Language
English
In and out
Text, Screens → Actions
Interaction
Agentic
Environment
Desktop apps, KiCad
Items from
Written by experts
Run by
Anyone
Occupations
Architecture and engineering
Human time
1 to 15 minutes
In views
Computer use, Agents
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
July 2026
Scores refreshed
November 20th, 2026
10
Models scored on its own leaderboard

2 models share the top score of 24% among models released by July 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in July 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 Native computer use 24%
  2. 2 Claude Fable 5 Function calling 24%
  3. 3 Claude Sonnet 4.5 Native computer use 20%
  4. 4 Claude Haiku 4.5 Native computer use 20%
  5. 5 Gemini 3.1 Pro Function calling 20%
  6. 6 Gemini 3.5 Flash Native computer use 20%
  7. 7 GPT-5.6 Sol Function calling 20%
  8. 8 Claude Opus 4.8 Native computer use 16%
  9. 9 Muse Spark 1.1 Function calling 16%
  10. 10 Gemini 3 Flash Function calling 4.00%

Source: Official Cua-Bench EDA (KiCad v1) leaderboard

#ModelScoreSettingDateSource
1 GPT-5.5 24% Native computer use Apr 2026 Official leaderboard
2 Claude Fable 5 24% Function calling Jun 2026 Official leaderboard
3 Claude Sonnet 4.5 20% Native computer use Sep 2025 Official leaderboard
4 Claude Haiku 4.5 20% Native computer use Oct 2025 Official leaderboard
5 Gemini 3.1 Pro 20% Function calling Feb 2026 Official leaderboard
6 Gemini 3.5 Flash 20% Native computer use May 2026 Official leaderboard
7 GPT-5.6 Sol 20% Function calling Jul 2026 Official leaderboard
8 Claude Opus 4.8 16% Native computer use May 2026 Official leaderboard
9 Muse Spark 1.1 16% Function calling Jul 2026 Official leaderboard
10 Gemini 3 Flash 4.00% Function calling Dec 2025 Official leaderboard

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 Jul 2026
GPT-5.5 24%

Source: Official Cua-Bench EDA (KiCad v1) 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% 2026 Near the ceiling (85%) GPT-5.5 Claude Sonnet 4.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5

Source: Official Cua-Bench EDA (KiCad v1) 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

9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 10 models we track.
  • Pass Newest score The newest is from July 2026, for GPT-5.6 Sol.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Pass Headroom The best is 24%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on cua.ai: 10 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