Skip to content

Video models

Silent and audio-enabled text-to-video and image-to-video rankings.

Snapshot: September 20, 2026

Silent image-to-video

Silent image-to-video Elo · Higher is better

Eligible
76
Candidates
76
Coverage
100.0%
Rank Model Creator Silent image-to-video Elo Since prior snapshot
1 Gemini Omni Flash Google 1,369 Not comparable
2 Wan 3.0 Alibaba 1,361 Not comparable
3 Bach 1.0 Pro Video Rebirth 1,359 Not comparable

Audio-enabled image-to-video

Audio-enabled image-to-video Elo · Higher is better

Eligible
35
Candidates
35
Coverage
100.0%
Rank Model Creator Audio-enabled image-to-video Elo Since prior snapshot
1 Minimax H3 Max (post-trained by fal) Fal 1,195 Not comparable
2 MiniMax H3 MiniMax 1,181 Not comparable
3 Gemini Omni Flash Google 1,177 Not comparable

Silent image-to-video segments

Silent image-to-video Elo · Higher is better

Eligible
0
Candidates
0
Coverage
0.0%

suppressed stale source

No exact-snapshot category observations are available for this run.

Silent text-to-video

Silent text-to-video Elo · Higher is better

Eligible
83
Candidates
83
Coverage
100.0%
Rank Model Creator Silent text-to-video Elo Since prior snapshot
1 Wan 3.0 Alibaba 1,336 Not comparable
2 Gemini Omni Flash Google 1,330 Not comparable
3 MiniMax H3 MiniMax 1,302 Not comparable

Audio-enabled text-to-video

Audio-enabled text-to-video Elo · Higher is better

Eligible
36
Candidates
36
Coverage
100.0%
Rank Model Creator Audio-enabled text-to-video Elo Since prior snapshot
1 Gemini Omni Flash Google 1,233 Not comparable
2 Wan 3.0 Alibaba 1,229 Not comparable
3 Minimax H3 Max (post-trained by fal) Fal 1,227 Not comparable

Silent text-to-video segments

Silent text-to-video Elo · Higher is better

Eligible
0
Candidates
0
Coverage
0.0%

suppressed stale source

No exact-snapshot category observations are available for this run.

Data source: Artificial Analysis .