Skip to content

Benchmark

CADGenBench · Generation

Scores are percentages. Higher is better.

Models and systems measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

39.8%
Mean
40.9%
Median
3.2%
Std dev
36.6%
10th percentile
44.4%
90th percentile
36.6%
Min
36.6%44.4%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1Grok 4.7Mecado · generation split · provider harnesses · reward · high effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.44.4%
2GPT-5.6 SolMecado · generation split · provider harnesses · reward · xhigh effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.37.1%
3Claude Opus 5Mecado · generation split · provider harnesses · reward · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.6%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Grok 4.6Mecado · generation split · provider harnesses · reward · high effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.40.9%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.