Benchmark Almanac

Wojak-Bench 3D

GPT-6.2 Astra 1,273 leads since November 2026
Not in model cards

Models turn the same drawing into a three-dimensional figure. Voters compare two anonymous prints or renders and choose which better matches the drawing.

The board fits Bradley-Terry ratings and counts ties as half a win. It documents exceptions to the three-attempt limit.

Made by
Andon Labs
Kind
CAD models
Level
University
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Measures
Preference
In and out
Images → 3D
Interaction
Single turn
Items from
Live play or votes
Refresh
One fixed set
Run by
A host
Occupations
Arts, design, entertainment, sports and media
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
10
Models scored on its own leaderboard

GPT-6.2 Astra leads with 1,273

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.

Bars start at 600.

  1. 1 GPT-6.2 Astra 1,273
  2. 2 Gemini 4 Carbon 1,202
  3. 3 GPT-6.2 Sol 1,159
  4. 4 Gemini 4 Neon 1,054
  5. 5 GPT-6 Astra 1,036
  6. 6 Claude Fable 5.2 1,010
  7. 7 GPT-6.1 Sol 999
  8. 8 Claude Opus 5.5 879
  9. 9 Claude Sonnet 5.5 682
  10. 10 Grok 4.7 670

Source: Official Wojak-Bench 3D leaderboard

#ModelScoreSettingDateSource
1 GPT-6.2 Astra 1,273 Nov 2026 Official leaderboard
2 Gemini 4 Carbon 1,202 Oct 2026 Official leaderboard
3 GPT-6.2 Sol 1,159 Nov 2026 Official leaderboard
4 Gemini 4 Neon 1,054 Nov 2026 Official leaderboard
5 GPT-6 Astra 1,036 Sep 2026 Official leaderboard
6 Claude Fable 5.2 1,010 Nov 2026 Official leaderboard
7 GPT-6.1 Sol 999 Sep 2026 Official leaderboard
8 Claude Opus 5.5 879 Sep 2026 Official leaderboard
9 Claude Sonnet 5.5 682 Sep 2026 Official leaderboard
10 Grok 4.7 670 Sep 2026 Official leaderboard

3 models have held number one on the official leaderboard since 2023

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

OpenAI Google DeepMind
Own leaderboard 3 leaders

Source: Official Wojak-Bench 3D 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
600 800 1,000 1,200 1,400 2027 600 800 1,000 1,200 1,400 2027

Source: Official Wojak-Bench 3D 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 (10 entries).
  • Pass Models scored 10 models we track.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Pass Frontier models 7 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Scored as an Elo rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on wojak-bench.dev.pion.dev: 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