# BenchCAD 2.1 Core, with tools (BenchCAD 2.1 (tools))

> BenchCAD 2.1 Core with tool access, in which a model writes CAD code that reproduces a target part.

Canonical page: https://benchlm.ai/benchmarks/benchcad21withtools

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: November 11, 2026

## About BenchCAD 2.1 (tools)

- Year: 2026
- Tasks: BenchCAD 2.1 Core set
- Format: Score (0-100)
- Difficulty: CAD generation
- Paper: [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf)

Anthropic reports BenchCAD 2.1 Core with tools at max effort, averaged over five runs. Display-only; first added from the Claude Fable 5.2 launch.

BenchCAD 2.1 (tools) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (3 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Fable 5.2](/models/claude-fable-5-2) | Anthropic | 83.5% |
| 2 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 65.3% |
| 3 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 44.4% |

## FAQ

### What does BenchCAD 2.1 (tools) measure?

BenchCAD 2.1 Core with tool access, in which a model writes CAD code that reproduces a target part.

### Which model scores highest on BenchCAD 2.1 (tools)?

Claude Fable 5.2 by Anthropic currently leads with a score of 83.5% on BenchCAD 2.1 (tools).

### How many models are evaluated on BenchCAD 2.1 (tools)?

3 AI models have published results on BenchCAD 2.1 (tools) in the BenchLM catalog.

### Does BenchCAD 2.1 (tools) affect BenchLM's overall score?

Not directly. BenchCAD 2.1 (tools) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on BenchCAD 2.1 (tools)

- [Claude Fable 5.2 vs Claude Opus 5.5](/compare/claude-fable-5-2-vs-claude-opus-5-5)
- [Claude Opus 5.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-opus-5-5)