ChartBmkAgent: leaderboard
ChartBmkAgent tests chart reading and reasoning on 300 synthesized chart-question pairs targeting 60 pre-specified failure descriptions across four domains. Accuracy is reference-answer correctness; provider-default thinking is retained except for eight documented timeout/revision cases. This is a targeted generated stress set, not a population sample of chart tasks.
Metric: Accuracy (%), 300 generated chart questions. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 84.3 | #36 |
| 2 | GPT-5.5 | 82.7 | #56 |
| 3 | Gemini 3.6 Flash | 80.7 | #84 |
| 4 | Claude Opus 4.8 | 80.3 | #64 |
| 5 | Gemini 3.5 Flash | 80.3 | #110 |
| 6 | Kimi K2.6 | 76.3 | #197 |
| 7 | Qwen 3.6 27B | 74.3 | #358 |
| 8 | Nex N2 Pro | 74.3 | #211 |
| 9 | Grok 4.5 | 74 | #91 |
| 10 | Grok 4.3 | 70 | #351 |
| 11 | GLM-4.6V | 66.7 | #721 |
| 12 | Kimi K2.5 | 63 | #272 |
| 13 | Claude Opus 4.6 | 61.3 | #114 |
| 14 | Claude Sonnet 5 | 50.7 | #124 |
| 15 | Mistral Medium 3.5 | 42.3 | #742 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=chartbmkagent · How It Works · Data refreshed daily, snapshot 2026-11-22.