Tests rebuilding parts, assemblies and circuit boards from drawings and images, helping you assess AI support for client design and prototyping work. Scores award partial credit, and tool-assisted runs are separate from standard runs; manufacturing still requires validation.
| Model / creator | Version | Reported score |
|---|---|---|
 Claude Fable 5.2Anthropic · Proprietary | 2.1 / Core / with tools | 83.5% |
| Claude Fable 5.2Anthropic · Proprietary | 2.1 / Core / standard | 75.4% |
| Claude Opus 5.5Anthropic · Proprietary | 2.1 / Core / with tools | 65.3% |
| Claude Opus 5.5Anthropic · Proprietary | 2.1 / Core / standard | 49% |
| Claude Fable 5.1Anthropic · Proprietary | 2.1 / Core / with tools | 44.4% |
| Claude Fable 5.1Anthropic · Proprietary | 2.1 / Core / standard | 36.3% |
effort: max · 100 Core cases; five runs; mean partial credit; official scorer. Extra tool-assisted setup has no token/round cap; standard setup has 60 rounds and 500K output tokens. No numeric confidence interval inferred from chart. · Tools enabled
Anthropic ↗effort: max · 100 Core cases; five runs; mean partial credit; official scorer. Extra tool-assisted setup has no token/round cap; standard setup has 60 rounds and 500K output tokens. No numeric confidence interval inferred from chart. · Tools enabled
Anthropic ↗effort: max · 100 Core cases; five runs; mean partial credit; official scorer. Extra tool-assisted setup has no token/round cap; standard setup has 60 rounds and 500K output tokens. No numeric confidence interval inferred from chart. · Tools enabled
Anthropic ↗effort: max · 100 Core cases; five runs; mean partial credit; official scorer. Extra tool-assisted setup has no token/round cap; standard setup has 60 rounds and 500K output tokens. No numeric confidence interval inferred from chart. · No tools
Anthropic ↗effort: max · 100 Core cases; five runs; mean partial credit; official scorer. Extra tool-assisted setup has no token/round cap; standard setup has 60 rounds and 500K output tokens. No numeric confidence interval inferred from chart. · No tools
Anthropic ↗effort: max · 100 Core cases; five runs; mean partial credit; official scorer. Extra tool-assisted setup has no token/round cap; standard setup has 60 rounds and 500K output tokens. No numeric confidence interval inferred from chart. · No tools
Anthropic ↗Tests research report tasks, helping you compare assistants for gathering and organizing material before advising clients.
LiveBench: CodingTests coding tasks, helping you compare models for implementation work that you would otherwise write or debug yourself.
GDPval-AACompares the quality of professional work products such as documents, spreadsheets and slides, helping you choose a model for preparing client deliverables.
