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

#ModelScoreOverall rank
1GPT-5.6 Sol84.3#36
2GPT-5.582.7#56
3Gemini 3.6 Flash80.7#84
4Claude Opus 4.880.3#64
5Gemini 3.5 Flash80.3#110
6Kimi K2.676.3#197
7Qwen 3.6 27B74.3#358
8Nex N2 Pro74.3#211
9Grok 4.574#91
10Grok 4.370#351
11GLM-4.6V66.7#721
12Kimi K2.563#272
13Claude Opus 4.661.3#114
14Claude Sonnet 550.7#124
15Mistral Medium 3.542.3#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.