RankingBenchCAD · Vision2Code 1000-file subset
BenchCAD · Vision2Code 1000-file subset
- Bucket
- Supporting evidence
- Unit
- index
- Direction
- Higher is better
- Version
- Vision2Code 1000-file subset
- Display harness
- Claude Fable 5.1 and Claude Mythos 5.1 System Card
- Board
- https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card
The available records have no admitted matched comparison in the capability core. Raw results remain available below.
Compare published benchmark results with category weights →
Models
1–8 of 8 entries
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| Claude Fable 5.1Anthropic | 0.437 voxel IoUReported settings & sourceRandom1000 of17900files; five runs; adaptive thinking max; no tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-09-24 | Claude Fable 5.1 and Claude Mythos 5.1 System Card | lab self-report | 2026-09-24 |
| Claude Fable 5Anthropic | 0.376 voxel IoUReported settings & sourceRandom1000 of17900files; five runs; adaptive thinking max; no tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-09-24 | Claude Fable 5.1 and Claude Mythos 5.1 System Card | lab self-report | 2026-09-24 |
| Claude Opus 5Anthropic | 0.366 voxel IoUReported settings & sourceRandom1000 of17900files; five runs; adaptive thinking max; no tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-09-24 | Claude Fable 5.1 and Claude Mythos 5.1 System Card | lab self-report | 2026-09-24 |
| Claude Fable 5Anthropic | 0.675 voxel IoUReported settings & sourceRandom1000 of17900files; five runs; adaptive thinking max; with tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-09-24 | Claude Fable 5.1 and Claude Mythos 5.1 System Card | lab self-report | 2026-09-24 |
| Claude Fable 5.1Anthropic | 0.843 voxel IoUReported settings & sourceRandom1000 of17900files; five runs; adaptive thinking max; with tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-09-24 | Claude Fable 5.1 and Claude Mythos 5.1 System Card | lab self-report | 2026-09-24 |
| Claude Opus 5Anthropic | 0.821 voxel IoUReported settings & sourceRandom1000 of17900files; five runs; adaptive thinking max; with tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-09-24 | Claude Fable 5.1 and Claude Mythos 5.1 System Card | lab self-report | 2026-09-24 |
| Claude Opus 5.5Anthropic | 0.73 voxel IoUReported settings & sourceRandom 1,000 of 17,900 Vision2Code files; five runs; adaptive thinking at max effort; no tools; views rendered at 256x256 px, the resolution Anthropic says matches the reference implementation. Provider-published lab self-report from the Claude Opus 5.5 system card (SHA256 7311c9c6bbb16d012f1c12c7418b05949fcf7ae3e30d2c40f22050074b2a7378). Not an independent board. Earlier cards used 128x128 px renders. This section publishes the corrected resolution. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Claude Opus 5.5 System Card · section 8.13.2 · reviewed 2026-09-22 | Claude Opus 5.5 System Card | lab self-report | 2026-09-22 |
| Claude Opus 5.5Anthropic | 0.962 voxel IoUReported settings & sourceRandom 1,000 of 17,900 Vision2Code files; five runs; adaptive thinking at max effort; with tools (container, image files, standard libraries, and an image cropping tool); 256x256 px views. Provider-published lab self-report from the Claude Opus 5.5 system card (SHA256 7311c9c6bbb16d012f1c12c7418b05949fcf7ae3e30d2c40f22050074b2a7378). Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Claude Opus 5.5 System Card · section 8.13.2 · reviewed 2026-09-22 | Claude Opus 5.5 System Card | lab self-report | 2026-09-22 |