ChartQA-Pro — Harder ChartQA-Pro subset, no-tools mode; distinct subset from base ChartQA
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | 69.4 | 1 | 2026-06-01 |
| 2 | Claude Opus 4.7 | Anthropic | 67.6 | 1 | 2026-06-01 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.