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

CADBench

An open multimodal benchmark for AI-assisted CAD program generation.

Data verified 26 confirmed releases in the last 30 daysStart free brief

Benchmark score on CADBench — August 12, 2026

BenchLM mirrors the published score view for CADBench. Grok 4.6 leads the public snapshot at 87.8% , followed by GPT-5.6 Sol (86.5%) and Grok 4.5 (83.7%). We do not use these results to rank models overall.

1Closed

Grok 4.6

xAI

grok-4-6

87.8%
Overall 62.44Context 500K
2Closed

GPT-5.6 Sol

OpenAI

gpt-5-6-sol

86.5%
Overall 81.23Context 1.05M
3Closed

Grok 4.5

xAI

grok-4-5

83.7%
Overall 75.42Context 500K
3 modelsCodingCurrentDisplay onlyUpdated August 12, 2026

Benchmark score table (3 models)

Score
1
Grok 4.6xAI · Closed
87.8%
2
GPT-5.6 SolOpenAI · Closed
86.5%
3
Grok 4.5xAI · Closed
83.7%

The published CADBench snapshot places Grok 4.6 first at 87.8%. The third row is 4.1 points behind. The broader top-10 range is 4.1 points, so many of the published results sit in a relatively narrow band.

3 models have been evaluated on CADBench. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. CADBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About CADBench

Year

2026

Tasks

Multimodal CAD program-generation tasks

Format

Task score

Difficulty

Professional CAD programming

The evaluation code and leaderboard submission process are public. BenchLM stores xAI's comparison rows as display-only because the exact run configuration comes from the model card.

CADBench

BenchLM freshness & provenance

Version

CADBench 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 CADBench measure?

An open multimodal benchmark for AI-assisted CAD program generation.

Which model scores highest on CADBench?

Grok 4.6 by xAI currently leads with a score of 87.8% on CADBench.

How many models are evaluated on CADBench?

3 AI models have been evaluated on CADBench on BenchLM.

Compare Top Models on CADBench

Grok 4.6 vs GPT-5.6 SolGPT-5.6 Sol vs Grok 4.5
Last updated: August 12, 2026 · BenchLM version CADBench 2026

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.