AI Model Release Tracker
Chart reasoning

CharXiv Reasoning

Can the AI read and reason about complex charts and figures, not just text? Higher is better.

Rankings

Higher is better
#1
Muse Spark
88.9%
2
Muse Spark 1.1
88.4%
2
Qwen3.8-Max
88.4%
4
Kimi K3
84.8%
5
Gemini 3.5 Flash
84.2%
6
GPT-5.5
84.1%
7
Gemini 3.1 Pro
83.3%
8
Claude Opus 4.7
82.1%
9
Qwen3.5OW
80.8%
10
Gemini 3.0 Flash
80.3%
11
Qwen3.6OW
78%
12
Claude Sonnet 4.6
72.4%

CharXiv Reasoning — frequently asked questions

What is CharXiv Reasoning?
Can the AI read and reason about complex charts and figures, not just text? Higher is better.
Which AI model scores highest on CharXiv Reasoning?
Muse Spark by Meta holds the best CharXiv Reasoning result among tracked models, at 88.9% (released Apr 8 2026). Higher scores are better on this benchmark.
What are the top 5 models on CharXiv Reasoning?
1. Muse Spark (Meta) — 88.9%; 2. Muse Spark 1.1 (Meta) — 88.4%; 2. Qwen3.8-Max (Qwen) — 88.4%; 4. Kimi K3 (Moonshot AI) — 84.8%; 5. Gemini 3.5 Flash (Google) — 84.2%.
How many models have a published CharXiv Reasoning score?
12 tracked models have a published CharXiv Reasoning score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.
What is the best open model on CharXiv Reasoning?
Qwen3.5 by Qwen is the highest-ranked model with downloadable weights on CharXiv Reasoning, scoring 80.8% at rank 9 overall.
← All benchmarks