BenchCAD 2.1 Core, without tools (BenchCAD 2.1)
We show this table for reference; we do not rank on it.
Hardware-engineering benchmark in which a model writes CAD code that reproduces a target part, scored 0 to 100 on the Core set.
Benchmark score on BenchCAD 2.1 — November 11, 2026
We compile the BenchCAD 2.1 rows from provider self-reports. Claude Fable 5.2 leads the table at 75.4%, followed by Claude Opus 5.5 (49.0%) and Claude Fable 5.1 (36.3%). We do not use these results to rank models overall.
Claude Fable 5.2
Anthropic
Claude Opus 5.5
Anthropic
Claude Fable 5.1
Anthropic
3 modelsMultimodal & GroundedCurrentDisplay onlyUpdated November 11, 2026
Benchmark score table (3 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Fable 5.2Anthropic | 75.4% | Not reported | Closed |
| 2 | Claude Opus 5.5Anthropic | 49.0% | Not reported | Closed |
| 3 | Claude Fable 5.1Anthropic | 36.3% | Not reported | Closed |
Among the reported BenchCAD 2.1 rows, Claude Fable 5.2 is first at 75.4%. The third row is 39.1 points behind. The broader top-10 range is 39.1 points, so the table still separates the published systems.
3 models have been evaluated on BenchCAD 2.1. The benchmark falls in the Multimodal & Grounded category. BenchCAD 2.1 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About BenchCAD 2.1
Year
2026
Tasks
BenchCAD 2.1 Core set
Format
Score (0-100)
Difficulty
CAD generation
Anthropic reports BenchCAD 2.1 Core scores with adaptive thinking at max effort, averaged over five runs. It is a newer version than the BenchCAD Vision2Code subset stored separately, so the lanes are not comparable. Display-only; first added from the Claude Fable 5.2 launch.
Freshness and provenance
Version
BenchCAD 2.1 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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.
Questions
What does BenchCAD 2.1 measure?
Hardware-engineering benchmark in which a model writes CAD code that reproduces a target part, scored 0 to 100 on the Core set.
Which model scores highest on BenchCAD 2.1?
Claude Fable 5.2 by Anthropic currently leads with a score of 75.4% on BenchCAD 2.1.
How many models are evaluated on BenchCAD 2.1?
3 AI models have published results on BenchCAD 2.1 in the BenchLM catalog.
Compare top models on BenchCAD 2.1
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.