Mistral Large 4 Preview - ChartQA Pro: leaderboard
Mistral Large 4 public-preview post (2026-10-06): ChartQA Pro, the harder successor to ChartQA with more diverse charts, dashboards and infographics, as reported by Mistral for five models. Scoring, prompting and reasoning effort are not stated; values are read from the post's chart. Score (%), higher is better.
Metric: Score (%). Source: mistral.ai. Saturation forecast: Around 2030. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 65.1 | #6 |
| 2 | Mistral Large 4 | 63.1 | #106 |
| 3 | Kimi K3 | 61.7 | #35 |
| 4 | Mistral Medium 3.5 | 55.4 | #375 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=mistral-large-4-preview-chartqa-pro · How It Works · Data refreshed daily, snapshot 2026-11-05.