ChartFI - Informativeness: leaderboard
Metric: Informativeness (0-1): mean semantic-level weight of the generated insights, weighting higher-level perceptual and domain insights more, with weights adapted to the reference description, descriptions of the 896 ChartFI-Bench scientific charts (arXiv papers accepted at peer-reviewed venues), temperature 0 and top-p 1; higher is better. Source: arxiv.org. Saturation forecast: Around 2036. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 0.32 |
| 2 | Llama 4 Scout | 0.31 |
| 3 | Claude Sonnet 4.6 | 0.3 |
| 4 | Qwen 3.5 Plus | 0.29 |
| 5 | Gemini 3 Flash | 0.28 |
| 6 | Qwen 3.5 27B | 0.27 |
Interactive version: theaggregate.ai/benchmark?slug=chartfi-informativeness · How It Works · Data refreshed daily, snapshot 2026-10-07.