multimodal benchmark
CharXiv-D Leaderboard
CharXiv-D is the descriptive questions subset of the CharXiv benchmark, designed to assess multimodal large language models' ability to extract basic information from scientific charts. It contains descriptive questions covering information extraction, enumeration, pattern recognition, and counting across 2,323 diverse charts from arXiv papers, all curated and verified by human experts.
Updated Aug 17, 2026
Models17
Model coverage17
MetricScore
EvidenceB
CharXiv-D Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score95.5% | Percentile100.0% | Participants17 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score94.6% | Percentile93.8% | Participants17 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score90.5% | Percentile87.5% | Participants17 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score90.2% | Percentile81.3% | Participants17 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score90.0% | Percentile75.0% | Participants17 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score88.4% | Percentile68.8% | Participants17 | EvidenceC | Evaluated |
| Rank07 | ModelCO | Score88.0% | Percentile62.5% | Participants17 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score87.9% | Percentile56.3% | Participants17 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score86.9% | Percentile50.0% | Participants17 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score85.9% | Percentile43.8% | Participants17 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score85.5% | Percentile37.5% | Participants17 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score85.3% | Percentile31.3% | Participants17 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score83.9% | Percentile25.0% | Participants17 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score83.0% | Percentile18.8% | Participants17 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score76.2% | Percentile12.5% | Participants17 | EvidenceC | Evaluated |
| Rank16 | ModelOP | Score73.9% | Percentile6.3% | Participants17 | EvidenceC | Evaluated |
| Rank17 | ModelCO | Score60.0% | Percentile0.0% | Participants17 | EvidenceC | Evaluated |
CharXiv-D Highlights
The leading models and scores on this benchmark.
CharXiv-D Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CharXiv-D
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis charxiv-d AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01BYSeed 2.1 ProByteDance
- Score
- 95.5%
Strengths
- Ranks #1 of 17 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharXiv-D, not total model capability
- 02BYSeed 2.1 TurboByteDance
- Score
- 94.6%
Strengths
- Ranks #2 of 17 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharXiv-D, not total model capability
- 03ACQwen3 VL 32B InstructAlibaba Cloud / Qwen Team
- Score
- 90.5%
Strengths
- Ranks #3 of 17 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharXiv-D, not total model capability
- 04ACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen Team
- Score
- 90.2%
Strengths
- Ranks #4 of 17 compared models
- 81th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharXiv-D, not total model capability
- 05OPGPT-4.5OpenAI
- Score
- 90.0%
- Speed
- Up to 50 tok/s via OpenAI
Strengths
- Ranks #5 of 17 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharXiv-D, not total model capability
Selection summary
Best AI Models for CharXiv-D
Seed 2.1 Pro currently leads CharXiv-D with 95.5%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is CharXiv-D?
What CharXiv-D measures and how its scores work.
CharXiv-D is the descriptive questions subset of the CharXiv benchmark, designed to assess multimodal large language models' ability to extract basic information from scientific charts. It contains descriptive questions covering information extraction, enumeration, pattern recognition, and counting across 2,323 diverse charts from arXiv papers, all curated and verified by human experts.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CharXiv-D
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- charxiv-d|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CharXiv-D.
Which model scores highest on CharXiv-D?
Seed 2.1 Pro is currently ranked first with 95.5%.
What does CharXiv-D measure?
CharXiv-D is the descriptive questions subset of the CharXiv benchmark, designed to assess multimodal large language models' ability to extract basic information from scientific charts. It contains descriptive questions covering information extraction, enumeration, pattern recognition, and counting across 2,323 diverse charts from arXiv papers, all curated and verified by human experts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.