LegendBench - Value Extraction: leaderboard
Value extraction in LegendBench (Zhang et al., 2026): questions that require recovering the quantitative value of a legend-bound mark, cell or color-scale position. Accuracy in percent; higher is better.
Metric: Value-extraction accuracy (%; legend-grounding questions: recover the quantitative value of the bound mark, cell or colour-scale position; LegendBench snapshot of 26,689 legend-centric chart questions generated from 900 base charts with counterfactual legend variants; the same prompt template and hyperparameters for every model). Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 78.31 | #29 |
| 2 | Qwen 3.5 27B | 62.28 | #358 |
| 3 | GPT-4.1 Mini | 57.69 | #775 |
| 4 | GLM-4.6V | 51.86 | #698 |
| 5 | Gemini 2.5 Flash | 47.63 | #452 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=legendbench-value-extraction · How It Works · Data refreshed daily, snapshot 2026-11-12.