multimodal benchmark
TOMATO
TOMATO (Temporal Reasoning Multimodal Evaluation) assesses multimodal models on motion and temporal perception in video, testing understanding of actions, motion, and changes over time.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
TOMATO Ranking
Higher score ranks better on this benchmark.
| 01 | BY | 79.5% | 100.0% | 2 | C | |
| 02 | BY | 56.8% | 0.0% | 2 | C |
TOMATO Score Distribution
A closer view of the leading scores on this benchmark.
TOMATO Highlights
The leading models and scores on this benchmark.
What is TOMATO?
What TOMATO measures and how its scores work.
TOMATO (Temporal Reasoning Multimodal Evaluation) assesses multimodal models on motion and temporal perception in video, testing understanding of actions, motion, and changes over time.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TOMATO
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- tomato|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about TOMATO.
Which model scores highest on TOMATO?
Seed 2.1 Pro is currently ranked first with 79.5%.
What does TOMATO measure?
TOMATO (Temporal Reasoning Multimodal Evaluation) assesses multimodal models on motion and temporal perception in video, testing understanding of actions, motion, and changes over time.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.