ChartAnno - Intent-Level Semantic Consistency: leaderboard

Metric: Semantic consistency (out of 5): mean of semantic faithfulness and semantic clarity, each an integer rubric score from 1 to 5 given by a GPT-5.4 judge, 0 for failed or missing output; annotated chart code generated from the unannotated code of 1,200 real-world charts; chart code input only; intent-level instructions that state only the communicative intent. Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)3.69
2Gemini 3 Flash (Preview)3.59
3GPT-5.43.56
4Claude Sonnet 4.63.49
5Kimi K2.53.32
6Gemma 4 31B3.2
7Qwen 3.5 397B A17B3.08
8Qwen 3.5 27B2.97
9Qwen 3.5 122B A10B2.93
10Qwen 3.5 9B2.31

Interactive version: theaggregate.ai/benchmark?slug=chartanno-intent-level-semantic-consistency · How It Works · Data refreshed daily, snapshot 2026-09-26.