Skip to main content

CharXiv Reasoning (CharXiv)

A scientific chart reasoning benchmark that tests whether models can understand, interpret, and reason about complex scientific visualizations including plots, diagrams, and data charts.

Top models on CharXiv — May 22, 2026

As of May 22, 2026, Claude Mythos Preview leads the CharXiv leaderboard with 93.2% , followed by Claude Opus 4.7 (Adaptive) (91%) and Muse Spark (86.4%).

21 modelsMultimodal & Grounded20% of category scoreRefreshingUpdated May 22, 2026

According to BenchLM.ai, Claude Mythos Preview leads the CharXiv benchmark with a score of 93.2%, followed by Claude Opus 4.7 (Adaptive) (91%) and Muse Spark (86.4%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.

21 models have been evaluated on CharXiv. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. Within that category, CharXiv contributes 20% of the category score, so strong performance here directly affects a model's overall ranking.

About CharXiv

Year

2024

Tasks

Scientific chart reasoning

Format

Chart understanding and reasoning

Difficulty

Scientific visualization reasoning

CharXiv evaluates a model's ability to reason about real-world scientific charts rather than simple visual QA. With-tools and without-tools variants isolate raw visual reasoning from tool-augmented performance.

BenchLM freshness & provenance

Version

CharXiv 2024

Refresh cadence

Annual

Staleness state

Refreshing

Question availability

Public benchmark set

Refreshing

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Leaderboard (21 models)

1
93.2%
2
91%
3
86.4%
4
84.2%
5
82.8%
6
82.1%
7
81.5%
8
81.4%
9
81%
10
80.8%
11
80.4%
12
80.2%
13
78.4%
14
78%
15
77.4%
16
77.2%
18
73.2%
19
68.5%
20
60.9%
21
52.7%

FAQ

What does CharXiv measure?

A scientific chart reasoning benchmark that tests whether models can understand, interpret, and reason about complex scientific visualizations including plots, diagrams, and data charts.

Which model scores highest on CharXiv?

Claude Mythos Preview by Anthropic currently leads with a score of 93.2% on CharXiv.

How many models are evaluated on CharXiv?

21 AI models have been evaluated on CharXiv on BenchLM.

Last updated: May 22, 2026 · BenchLM version CharXiv 2024

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.