CADGenBench Generation

We show this table for reference; we do not rank on it.

Hugging Face's open benchmark for generating valid and geometrically correct 3D mechanical parts.

Generation score on CADGenBench Generation — November 12, 2026 snapshot

We mirror the published generation score view for CADGenBench Generation. Godela - Modernized Agentic leads the public snapshot at 90.2%, followed by build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) r2 (86.9%) and Godela (84.5%). We do not use these results to rank models overall.

Godela - Modernized Agentic

Godela

90.2%

build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) r2

Anthropic

86.9%

Godela

84.5%

26 modelsCodingCurrentDisplay onlyUpdated November 12, 2026 snapshot

Generation score table (26 models)

Generation score results for CADGenBench Generation
Rank	Model / configuration	Score	Parameters (B)	Open / closed
1	Godela - Modernized AgenticGodela	90.2%	Not reported	Unknown
2	build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) r2Anthropic	86.9%	Not reported	Unknown
3	GodelaGodela	84.5%	Not reported	Unknown
4	build123d-mcp-v0381-claude-opus-5-xhigh-full-r6Anthropic	59.6%	Not reported	Unknown
5	gpt-5.6-sol-xhigh-floor-chain-v0379OpenAI	45.1%	Not reported	Unknown
6	Archie in ForgeSatvik Adyanthaya	42.3%	Not reported	Unknown
7	Grok 4.6 high Mecado Baseline with Build123dxAI	41.5%	Not reported	Unknown
8	Grok 4.6 xhigh Mecado Baseline with Build123dxAI	39.1%	Not reported	Unknown
9	Claude Fable 5Anthropic	37.3%	Not reported	Closed
10	gpt-5.5-build123d-mcp-0.3.59-xhigh-r5OpenAI	37.2%	Not reported	Unknown
11	GPT-5.6 Sol xhigh Mecado Baseline with Build123dOpenAI	36.4%	Not reported	Unknown
12	Claude Opus 5 max Mecado Baseline with Build123dAnthropic	36.1%	Not reported	Unknown
13	GPT-5.6 Sol HF Baseline with Build123dOpenAI	35.5%	Not reported	Unknown
14	gpt-5.5-build123d-mcp-0.3.56-v2OpenAI	34.5%	Not reported	Unknown
15	GPT-5.5 Pro HF Baseline with Build123dOpenAI	32.1%	Not reported	Unknown
16	build123d-mcp + Claude Opus 4.8 (full, 81 fixtures)Anthropic	31.5%	Not reported	Unknown
17	Claude Opus 4.7 HF Baseline with Build123dAnthropic	29.9%	Not reported	Unknown
18	GPT-5.5OpenAI	29.7%	Not reported	Closed
19	Opus 4.8 — Claude Code + text-to-cad skillAnthropic	28.0%	Not reported	Unknown
20	Claude Opus 4.8Anthropic	27.4%	Not reported	Closed
21	Claude Opus 4.6 HF Baseline with Build123dAnthropic	23.6%	Not reported	Unknown
22	Gemini 3.1 Flash-Lite HF Baseline with Build123dGoogle	22.4%	Not reported	Unknown
23	Claude Sonnet 4.6Anthropic	22.1%	Not reported	Closed
24	Gemini 3.1 ProGoogle	21.1%	Not reported	Closed
25	GLM-4.6V HF Baseline with Build123dZ.AI	16.4%	Not reported	Unknown
26	Qwen3-VL 235B-A22B Instruct HF Baseline with Build123dAlibaba	16.3%	Not reported	Unknown

How we show CADGenBench Generation

We mirror 26 completed submissions that the official CADGenBench dataset marks validated. The visible score is the generation-task score; aggregate, editing, validity, version, and data-revision fields remain attached to each row.

CADGenBench Generation is display only. Each submission can include a different agent, CAD library, prompt, and tool configuration, so we do not treat the table as a normalized base-model comparison.

Snapshot

26 validated submissions49 generation tasks5 mapped baselinesDisplay only

Validated submissions dataset CADGenBench GitHub repository

The published CADGenBench Generation snapshot places Godela - Modernized Agentic first at 90.2%. The third row is 5.7 points behind. The broader top-10 range is 53.1 points, so the table still separates the published systems.

26 models have been evaluated on CADGenBench Generation. The benchmark falls in the Coding category. CADGenBench Generation is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About CADGenBench Generation

Year

2026

Tasks

49 CAD generation samples

Format

Validity-gated CAD score

Difficulty

Professional mechanical CAD

The benchmark repository, submission dataset, and hosted leaderboard are public. BenchLM stores the generation score separately from editing and keeps the model-card rows display-only.

CADGenBench Public benchmark source

Freshness and provenance

Version

CADGenBench Generation 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does CADGenBench Generation measure?

Hugging Face's open benchmark for generating valid and geometrically correct 3D mechanical parts.

Which model leads the published CADGenBench Generation snapshot?

Godela - Modernized Agentic currently leads the published CADGenBench Generation snapshot with 90.2% generation score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on CADGenBench Generation?

The November 12, 2026 snapshot snapshot contains 26 AI models.

Last updated: November 12, 2026 snapshot · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 7,000+ subscribers.

One email each week. Unsubscribe anytime.