multimodal benchmark
CharXiv-R Leaderboard
CharXiv-R is the reasoning component of the CharXiv benchmark for multimodal large language models.
Updated Sep 5, 2026
Models55
Model coverage55
MetricScore
EvidenceB
CharXiv-R Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score93.20% | Percentile100.00% | Participants55 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score91.30% | Percentile98.15% | Participants55 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score91.00% | Percentile96.30% | Participants55 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score90.60% | Percentile94.44% | Participants55 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score90.60% | Percentile92.59% | Participants55 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score90.20% | Percentile90.74% | Participants55 | EvidenceC | Evaluated |
| Rank07 | ModelAN | Score89.90% | Percentile88.89% | Participants55 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score89.40% | Percentile87.04% | Participants55 | EvidenceC | Evaluated |
| Rank09 | ModelZA | Score89.40% | Percentile85.19% | Participants55 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score88.70% | Percentile83.33% | Participants55 | EvidenceC | Evaluated |
| Rank11 | ModelME | Score88.40% | Percentile81.48% | Participants55 | EvidenceC | Evaluated |
| Rank12 | ModelAN | Score88.30% | Percentile79.63% | Participants55 | EvidenceC | Evaluated |
| Rank13 | ModelMA | Score86.70% | Percentile77.78% | Participants55 | EvidenceC | Evaluated |
| Rank14 | ModelME | Score86.40% | Percentile75.93% | Participants55 | EvidenceC | Evaluated |
| Rank15 | ModelBY | Score86.40% | Percentile74.07% | Participants55 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Score86.20% | Percentile72.22% | Participants55 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score85.90% | Percentile70.37% | Participants55 | EvidenceC | Evaluated |
| Rank18 | ModelGO | Score84.20% | Percentile68.52% | Participants55 | EvidenceC | Evaluated |
| Rank19 | ModelBY | Score83.60% | Percentile66.67% | Participants55 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score82.10% | Percentile64.81% | Participants55 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score81.60% | Percentile62.96% | Participants55 | EvidenceC | Evaluated |
| Rank22 | ModelAC | Score81.50% | Percentile61.11% | Participants55 | EvidenceC | Evaluated |
| Rank23 | ModelGO | Score81.40% | Percentile59.26% | Participants55 | EvidenceC | Evaluated |
| Rank24 | ModelOP | Score81.10% | Percentile57.41% | Participants55 | EvidenceC | Evaluated |
| Rank25 | ModelXI | Score81.00% | Percentile55.56% | Participants55 | EvidenceC | Evaluated |
| Rank26 | ModelGO | Score80.30% | Percentile53.70% | Participants55 | EvidenceC | Evaluated |
| Rank27 | ModelAC | Score79.50% | Percentile51.85% | Participants55 | EvidenceC | Evaluated |
| Rank28 | ModelME | Score78.80% | Percentile50.00% | Participants55 | EvidenceC | Evaluated |
| Rank29 | ModelOP | Score78.60% | Percentile48.15% | Participants55 | EvidenceC | Evaluated |
| Rank30 | ModelAC | Score78.40% | Percentile46.30% | Participants55 | EvidenceC | Evaluated |
CharXiv-R Highlights
The leading models and scores on this benchmark.
CharXiv-R Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CharXiv-R
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is CharXiv-R?
What CharXiv-R measures and how its scores work.
CharXiv-R is a multimodal benchmark component focused on complex reasoning questions involving scientific charts from arXiv papers.
It measures performance on reasoning tasks that require synthesizing information across visual chart elements, using the Score metric expressed as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CharXiv-R
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CharXiv-R.
Which model scores highest on CharXiv-R?
Claude Mythos Preview is currently ranked first with 93.20%.
What are the top three models on CharXiv-R?
The current leaders are Claude Mythos Preview (93.20%), Kimi K3 (91.30%), and Claude Opus 4.7 (91.00%).
Which CharXiv-R model has the lowest official input price?
GLM-5.3-Flash has the lowest matched official input price at $0.08 input / $0.25 output per 1M tokens.
Which models are fastest among CharXiv-R results?
The fastest matched records are GPT-4.1 mini (467.39 tok/s via OpenAI), Gemini 3.5 Flash (210.94 tok/s via Google), and GPT-5.5 Instant (206.89 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.