Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Advertise

Benchmark profile

CADGenBench Generation

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

How we show CADGenBench Generation

We mirror 19 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.

19 validated submissions49 generation tasks5 mapped baselinesDisplay only
Validated submissions datasetCADGenBench GitHub repository

Generation score on CADGenBench Generation — August 12, 2026 snapshot

BenchLM mirrors the published generation score view for CADGenBench Generation. build123d-mcp-v0381-claude-opus-5-xhigh-full-r6 leads the public snapshot at 59.6% , followed by gpt-5.6-sol-xhigh-floor-chain-v0379 (45.1%) and Archie in Forge (42.3%). We do not use these results to rank models overall.

1

build123d-mcp-v0381-claude-opus-5-xhigh-full-r6

Anthropic

pzfreo-build123d-mcp-v0381-claude-opus-5-xhigh-20260807-101147

59.6%
Overall —
2

gpt-5.6-sol-xhigh-floor-chain-v0379

OpenAI

pzfreo-gpt-5-6-sol-xhigh-floor-chain-v0379-20260717-045810

45.1%
Overall —
3

Archie in Forge

Satvik Adyanthaya

satvik-adyanthaya-archie-in-forge-20260711-184330

42.3%
Overall —
19 modelsCodingCurrentDisplay onlyUpdated August 12, 2026 snapshot

Generation score table (19 models)

Score
1
build123d-mcp-v0381-claude-opus-5-xhigh-full-r6Anthropic
59.6%
2
gpt-5.6-sol-xhigh-floor-chain-v0379OpenAI
45.1%
3
Archie in ForgeSatvik Adyanthaya
42.3%
4
Claude Fable 5Anthropic · Closed
37.3%
5
gpt-5.5-build123d-mcp-0.3.59-xhigh-r5OpenAI
37.2%
6
GPT-5.6 Sol HF Baseline with Build123dOpenAI
35.5%
7
gpt-5.5-build123d-mcp-0.3.56-v2OpenAI
34.5%
8
GPT-5.5 Pro HF Baseline with Build123dOpenAI
32.1%
9
build123d-mcp + Claude Opus 4.8 (full, 81 fixtures)Anthropic
31.5%
10
Claude Opus 4.7 HF Baseline with Build123dAnthropic
29.9%
11
GPT-5.5OpenAI · Closed
29.7%
12
Opus 4.8 — Claude Code + text-to-cad skillAnthropic
28.0%
13
Claude Opus 4.8Anthropic · Closed
27.4%
14
Claude Opus 4.6 HF Baseline with Build123dAnthropic
23.6%
15
Gemini 3.1 Flash-Lite HF Baseline with Build123dGoogle
22.4%
16
Claude Sonnet 4.6Anthropic · Closed
22.1%
17
Gemini 3.1 ProGoogle · Closed
21.1%
18
GLM-4.6V HF Baseline with Build123dZ.AI
16.4%
19
Qwen3-VL 235B-A22B Instruct HF Baseline with Build123dAlibaba
16.3%

The published CADGenBench Generation snapshot places build123d-mcp-v0381-claude-opus-5-xhigh-full-r6 first at 59.6%. The third row is 17.3 points behind. The broader top-10 range is 29.7 points, so the table still separates the published systems.

19 models have been evaluated on CADGenBench Generation. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. 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.

CADGenBenchPublic benchmark source

BenchLM freshness & 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.

FAQ

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?

build123d-mcp-v0381-claude-opus-5-xhigh-full-r6 currently leads the published CADGenBench Generation snapshot with 59.6% 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?

19 AI models are included in BenchLM's mirrored CADGenBench Generation snapshot, based on the public leaderboard captured on August 12, 2026 snapshot.

Last updated: August 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 2,000+ readers.

One email each week. Unsubscribe anytime.