CADGenBench Submissions: CAD Model Generation Benchmark Results

Submissions and evaluation results for the CADGenBench leaderboard. The dataset contains one row per submitted and evaluated entry, as read by the leaderboard table. It was created by HuggingAI4Engineering and last updated on June 10, 2026.

Use Cases

• Benchmarking CAD model generation models based on the leaderboard evaluation results
• Analyzing performance trends across different submissions to the CADGenBench challenge
• Training meta-models to predict AI performance on CAD generation tasks based on historical submission data

Strengths

• Directly linked to a public benchmark (CADGenBench) with a dedicated leaderboard space.
• Contains one evaluated entry per row, suggesting a structured format for comparison.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

HuggingAI4Engineering

Collection Method

Submissions to the CADGenBench leaderboard and subsequent evaluation.

Freshness

Last updated 2026-06-10 12:08:53; freshness should be verified.