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. Gemini 3.8 Flash (Google) — 86.2%; 5. Kimi K3 (Moonshot AI) — 84.8%.

How many models have a published CharXiv Reasoning score?

16 tracked models have a published CharXiv Reasoning score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

What is the best open model on CharXiv Reasoning?

Qwen3.8-Flash-Next by Qwen is the highest-ranked model with downloadable weights on CharXiv Reasoning, scoring 84.6% at rank 6 overall.

Chart reasoning

CharXiv Reasoning

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

CharXiv Reasoning with tools

Rankings

Higher is better

CharXiv Reasoning — frequently asked questions

: Can the AI read and reason about complex charts and figures, not just text? Higher is better.
: 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.
: 1. Muse Spark (Meta) — 88.9%; 2. Muse Spark 1.1 (Meta) — 88.4%; 2. Qwen3.8-Max (Qwen) — 88.4%; 4. Gemini 3.8 Flash (Google) — 86.2%; 5. Kimi K3 (Moonshot AI) — 84.8%.
: 16 tracked models have a published CharXiv Reasoning score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.
: Qwen3.8-Flash-Next by Qwen is the highest-ranked model with downloadable weights on CharXiv Reasoning, scoring 84.6% at rank 6 overall.