Benchmark
CharXiv Reasoning Benchmark
What is CharXiv Reasoning?
Chart reasoning benchmark with tool access. Scores depend on context length and tool configuration. Benchmark Radar tracks 1 reported scores for CharXiv…
- Released
- 2025-06-01
- Evaluates
- vision
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://github.com/CharXiv/CharXiv
CharXiv Reasoning code
CharXiv Reasoning results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5.3-Flash | Z.ai | 89.4 | 2026-08-27 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite CharXiv Reasoning?
- GLM-5.3-Flash Z.ai, 2026-08-27