Explains honest scaling in charts
Zero-based bars, marked non-zero line axes, shared scales for compared charts; Tufte's lie factor.
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 82% | Not shown |
| gpt-6-luna | Low cost | 99% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | Mastered |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: Zero-based bars, marked non-zero line axes, shared scales for compared charts; Tufte's lie factor.
How it is assessed: Answers a written question on the chart scaling correctly
Related knobits
Builds on
Needed for
- W-503 Recognises a truncated axis exaggerating a change
- W-504 Recognises comparable charts on different scales
- W-531 Rescales a chart so it shows the change truthfully
All 14 knobits of Specify reports and dashboards.
Source: Practice the stage 5 reference and review checklist rest on