Molmo 2 8B on UCF101-AD
19.5%Rank #9 of 9 on UCF101-AD
- Coverage
- Full (4224/4224)
- Cost per task
- —
- Median latency
- 0.2s
- Tokens per task
- 914 in · 2 out
Run setting: 1 fps.
Tokens and latency
Tokens per call
| Token type | Mean | Median | 90th pct. |
|---|---|---|---|
| Input | 914 | 793 | 1,133 |
| of which cached | 0 | 0 | 0 |
| Output | 2 | 2 | 2 |
Over 4,601 calls that returned an answer, including questions asked again after a failed attempt.
Latency
- Median
- 0.2s
- Mean
- 0.2s
- 90th percentile
- 0.3s
- 99th percentile
- 0.4s
We only consider the first question against a video for self hosted models, ignoring prefix caching latency.