Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Benchmarks · Agents & computer use · Science & research · Vision

SolidWorks-Bench

Real mechanical design in SolidWorks. From the engineering drawings of 73 machines, such as robots and CNC routers, the model builds every custom part and assembles the machine with mates that hold and move correctly. Mean reward across geometry, assembly function and CAD practice, one attempt each.

9 models · 9 results · updated 2026-11-17 · markovstudios.com ↗

Leaderboard

Fable 5.2 high

Score vs subscription cost per task

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's most subsidized plan, or API price with no plan data. 3 more models under All models in settings.

More from this benchmark

9 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Fable 5.2 high0.5733.663.951.255.5
GPT-6 Astra high0.4261.439.853.534.2
Sonnet 5.5 high0.3472.638.931.930.1
Opus 5.5 high0.3422.348.68.7337.2
Kimi K3.1 high0.196314.336.711.9
DeepSeek V4.1 Flash high0.1273.56.2132.16.15
Muse Spark Open high0.0733.54.0123.71.64
GLM 5.3 Flash high0.0646.78.0627.36.16
MiniMax M3.1 high0.0248.25.5129.64.83

All results

9 rows
#ModelEffortSolidWorks-BenchSubscription $ / taskAPI $ / taskAgent stepsTime
1Fable 5.2high57.3%$2.54$693633.6 h
2GPT-6 Astrahigh42.6%$1.68$471241.4 h
3Sonnet 5.5high34.7%$0.23$174092.6 h
4Opus 5.5high34.2%$0.32$253982.3 h
5Kimi K3.1high19.6%$7.18$112883.0 h
6DeepSeek V4.1 Flashhigh12.7%$0.080$1.123733.5 h
7Muse Spark Openhigh7.3%$13$132503.5 h
8GLM 5.3 Flashhigh6.4%$0.14$3.047386.7 h
9MiniMax M3.1high2.4%$7.75$151,4478.2 h