Text-to-Video
Step-Video-T2V is ranked in the Text-to-Video benchmark from Artificial Analysis.
926
Feb 2025
n/a
n/a
n/a
Category rows come directly from Artificial Analysis when the endpoint exposes category-level Elo scores.
| Category | Elo | 95% CI | Appearances |
|---|---|---|---|
| Action | 985 | -29/29 | 317 |
| Sci Fi | 985 | -22/22 | 705 |
| Sports | 984 | -31/31 | 360 |
| Transport | 982 | -17/17 | 1,623 |
| Buildings | 978 | -15/15 | 2,224 |
| Long prompt | 975 | -24/24 | 1,071 |
| People | 962 | -13/13 | 2,628 |
| Text | 959 | -29/29 | 541 |
| Multi-scene | 958 |
| -35/35 |
| 301 |
| Technology | 957 | -14/14 | 1,762 |
| Specific location or era | 955 | -23/23 | 992 |
| Physics | 946 | -15/15 | 1,791 |