Benchmark Almanac

AutoCAD Bench

GPT-5.6 Sol 46% leads since July 2026
Not in model cards

Computer-use agents turn a dimensioned reference drawing into a correct, editable DWG in AutoCAD through the screen alone, with mouse and keyboard. 50 tasks span 2D drafting and 3D modeling at four difficulty levels.

A task counts as completed at an evaluator score of 75 or more. The first report on July 23, 2026 tested seven models, and GPT-5.6 Sol completed 23 of 50 tasks. Typed commands and key presses made up 88.8% of the agents’ actions.

Made by
Markov
Released
July 2026
Kind
CAD models
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images, Screens → Actions, 3D
Interaction
Agentic
Environment
AutoCAD
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
July 2026
Scores refreshed
November 20th, 2026
7
Entries on its own leaderboard, 6 models we track

GPT-5.6 Sol leads with 46% among models released by July 2026 GPT-5.6 Sol leads with 46% among models released by July 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 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-5.6 Sol 46%
  2. 2 GPT-5.6 Terra 14%
  3. 3 Claude Fable 5 10%
  4. 4 GPT-5.6 Luna 8.00%
  5. 5 Qwen3.7 0%
  6. 6 Kimi K2.5 0%
  7. 7 Claude Opus 4.8 0%

Source: Official AutoCAD Bench leaderboard

#EntryScoreSettingDateSource
1 GPT-5.6 Sol 46% Jul 2026 Official leaderboard
2 GPT-5.6 Terra 14% Jul 2026 Official leaderboard
3 Claude Fable 5 10% Jun 2026 Official leaderboard
4 GPT-5.6 Luna 8.00% Jul 2026 Official leaderboard
5 Qwen3.7 0% Official leaderboard
6 Kimi K2.5 0% Jan 2026 Official leaderboard
7 Claude Opus 4.8 0% May 2026 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.6 Sol 46% Jul 2026 Official leaderboard
2 GPT-5.6 Terra 14% Jul 2026 Official leaderboard
3 Claude Fable 5 10% Jun 2026 Official leaderboard
4 GPT-5.6 Luna 8.00% Jul 2026 Official leaderboard
5 Kimi K2.5 0% Jan 2026 Official leaderboard
6 Claude Opus 4.8 0% May 2026 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s own leaderboard in 2 groups: modality and difficulty. Each ranks models on one part of the test. GPT-5.6 Sol leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

2D drafting

A complete Model Space drawing with geometry, dimensions, leaders, notes, center marks and centerlines. 21 tasks. 6 models we track have a score here.

  1. 1 GPT-5.6 Sol 66.7%
  2. 2 GPT-5.6 Terra 23.8%
  3. 3 GPT-5.6 Luna ↑1 19%
  4. 4 Claude Fable 5 ↓1 4.80%
  5. 5 Kimi K2.5 0%
  6. 6 Claude Opus 4.8 0%

2 models have held number one on the official leaderboard since its release in July 2026

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

Anthropic OpenAI
Own leaderboard Not tested since Jul 2026

Source: Official AutoCAD 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% 2026 Near the ceiling (85%) GPT-5.6 Sol Claude Fable 5 Kimi K2.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol Claude Fable 5

Source: Official AutoCAD 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 All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (7 entries).
  • Pass Models scored 6 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from July 2026, for GPT-5.6 Luna.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Pass Headroom The best is 46%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on markovstudios.com: 6 rows for models we track and 1 other entry 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