ChartBmkAgent: leaderboard

Metric: Accuracy (%), 300 generated chart questions. Source: arxiv.org. Saturation forecast: Around January 2027. 17 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol84.3
2GPT-5.582.7
3Gemini 3.6 Flash80.7
4Claude Opus 4.880.3
5Gemini 3.5 Flash80.3
6Kimi K2.676.3
7Qwen 3.6 27B74.3
8Nex N2 Pro74.3
9Grok 4.574
10Grok 4.370
11GLM-4.6V66.7
12Kimi K2.563
13Claude Opus 4.661.3
14Claude Sonnet 550.7
15Mistral Medium 3.542.3

Interactive version: theaggregate.ai/benchmark?slug=chartbmkagent · How It Works · Data refreshed daily, snapshot 2026-10-08.