ChartBmkAgent: leaderboard
Metric: Accuracy (%), 300 generated chart questions. Source: arxiv.org. Saturation forecast: Around January 2027. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 84.3 |
| 2 | GPT-5.5 | 82.7 |
| 3 | Gemini 3.6 Flash | 80.7 |
| 4 | Claude Opus 4.8 | 80.3 |
| 5 | Gemini 3.5 Flash | 80.3 |
| 6 | Kimi K2.6 | 76.3 |
| 7 | Qwen 3.6 27B | 74.3 |
| 8 | Nex N2 Pro | 74.3 |
| 9 | Grok 4.5 | 74 |
| 10 | Grok 4.3 | 70 |
| 11 | GLM-4.6V | 66.7 |
| 12 | Kimi K2.5 | 63 |
| 13 | Claude Opus 4.6 | 61.3 |
| 14 | Claude Sonnet 5 | 50.7 |
| 15 | Mistral Medium 3.5 | 42.3 |
Interactive version: theaggregate.ai/benchmark?slug=chartbmkagent · How It Works · Data refreshed daily, snapshot 2026-10-08.