multimodal benchmark
HR-Bench (4k)
HR-Bench (4k) evaluates image understanding on high-resolution visual inputs with a 4k setting.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
HR-Bench (4k) Ranking
Higher score ranks better on this benchmark.
| 1 | XI | 88.5% | 100.0% | 1 | C |
HR-Bench (4k) Highlights
The leading models and scores on this benchmark.
What is HR-Bench (4k)?
What HR-Bench (4k) measures and how its scores work.
HR-Bench (4k) evaluates image understanding on high-resolution visual inputs with a 4k setting.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- HR-Bench (4k)
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- hr-bench-4k|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about HR-Bench (4k).
Which model scores highest on HR-Bench (4k)?
MiMo-V2.5 is currently ranked first with 88.5%.
What does HR-Bench (4k) measure?
HR-Bench (4k) evaluates image understanding on high-resolution visual inputs with a 4k setting.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.