Domains: ScienceFinanceMedicalBusiness
Skills: MultimodalReasoningKnowledge Work

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
0/10
Access Model: Public Plaintext
"We release all tasks, images, provenance metadata, and evaluation code through the public dataset and code repositories, and will maintain the public leaderboard as new models launch."
Primary source (Paper) ↗ Verified 2026-11-19
"This repository contains 2 sample tasks from the full 100-task benchmark. To evaluate your models on the full set, contact benchmarks@surgehq.ai."

Originality

Weight 25%
7.2/10
Reuse Profile: Low Reuse (<25%)
"Each task was authored by a practitioner in the relevant field, accompanied by an explicit walkthrough of the visual and computational steps leading to the answer, and independently verified by three additional domain experts."
Primary source (Paper) ↗ Verified 2026-11-19

Freshness

Weight 20%
6/10
Initial Release: 2026-07Latest Refresh: 2026-07Rolling Updates: No
"Table 3 reports mean pass@1 for all 30 frontier model configurations in the launch snapshot (July 2026)"
Primary source (Paper) ↗ Verified 2026-11-19

Grading

Weight 15%
7.3/10
Integrity: Independent StandardizedSandbox: not applicable single turn
"Each model receives a single user message containing the task prompt followed by the chart image inline: no system prompt, no few-shot examples, no image normalization, and no tools (no code execution, cropping, or zooming)."
Primary source (Paper) ↗ Verified 2026-11-19

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit Chartography Tier C 4.1/10
[![BenchAudit Tier C](https://benchaudit.org/badges/chartography.svg)](https://benchaudit.org/benchmarks/chartography/)