multimodal benchmark
LiveSports-3K
LiveSports-3K evaluates fine-grained understanding and commentary of live sports video.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
LiveSports-3K Ranking
Higher score ranks better on this benchmark.
| 01 | BY | 77.1% | 100.0% | 2 | C | |
| 02 | BY | 76.8% | 0.0% | 2 | C |
LiveSports-3K Score Distribution
A closer view of the leading scores on this benchmark.
LiveSports-3K Highlights
The leading models and scores on this benchmark.
What is LiveSports-3K?
What LiveSports-3K measures and how its scores work.
LiveSports-3K evaluates fine-grained understanding and commentary of live sports video.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- LiveSports-3K
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- livesports-3k|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LiveSports-3K.
Which model scores highest on LiveSports-3K?
Seed 2.1 Turbo is currently ranked first with 77.1%.
What does LiveSports-3K measure?
LiveSports-3K evaluates fine-grained understanding and commentary of live sports video.
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.