Vision & documents

Chartography (tools) leaderboard

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap
License: https://creativecommons.org/licenses/by-nc/4.0/

As of 2026-10-29, the highest measured score on Chartography (tools) is 90.2% by Claude Sonnet 5.5. 5 more models have estimated scores, calibrated from the benchmarks they were measured on.

Measured scores: benchlm.ai.

#	Model	Score	Source
1	Claude Sonnet 5.5	90.2%	measured
2	Kimi K3.1 Pro	90.2%	measured
3	Claude Opus 5.5	89.0%	measured
4	Claude Opus 4.8	86.3%	estimated ± 5.9 pp, low confidence
5	Hy4 preview	86.3%	estimated ± 5.9 pp, low confidence
6	Kimi K3	84.1%	estimated ± 5.9 pp, low confidence
7	Claude Opus 5	83.0%	measured
8	DeepSeek V4.1 Flash 1017	83.0%	measured
9	Step 5 Preview	81.7%	estimated ± 5.9 pp, low confidence
10	Claude Fable 5	79.8%	estimated ± 5.9 pp, low confidence
11	GLM-5.3-Flash	78.0%	measured

All leaderboards

All leaderboards

Agentic · terminal

Agentic · tools

Coding

Math

Knowledge & reasoning

Instruction following

Multilingual

Vision & documents

Long context

General