multimodal benchmark
PerceptionTest Leaderboard
PerceptionTest is a multimodal video benchmark for evaluating perception and reasoning across video, audio, and text.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
PerceptionTest Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score73.20% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score70.50% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
PerceptionTest Highlights
The leading models and scores on this benchmark.
PerceptionTest Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PerceptionTest
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is PerceptionTest?
What PerceptionTest measures and how its scores work.
PerceptionTest contains 11.6k real-world videos averaging 23 seconds, filmed by participants worldwide and annotated with six types of labels.
It measures skills in Memory, Abstraction, Physics, and Semantics, along with descriptive, explanatory, predictive, and counterfactual reasoning, using Score as a ratio metric.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PerceptionTest
- 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 PerceptionTest.
Which model scores highest on PerceptionTest?
Qwen2.5 VL 72B Instruct is currently ranked first with 73.20%.
What are the top three models on PerceptionTest?
The current leaders are Qwen2.5 VL 72B Instruct (73.20%) and Qwen2.5 VL 7B Instruct (70.50%).
Which PerceptionTest model has the lowest official input price?
Qwen2.5 VL 7B Instruct has the lowest matched official input price at $0.35 input / $1.1 output per 1M tokens.
Which models are fastest among PerceptionTest results?
No matched runtime record is currently available.
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.