The Known Good Updated 8 Oct 2026 Subscribe

Video Arenas

Elo ratings from blind pairwise votes: a human is shown two anonymous outputs for the same prompt and picks the better one. The votes are collected and published by Arena — we ingest the ratings, we do not run the votes and we do not adjust them.

Text Image Video Speech

Video Arenas

Human preference rating from blind pairwise votes, ingested from Arena

Text to Video ArenaImage to Video Arena
Text to Video Arena

Elo from blind pairwise preference votes, collected and published by Arena. Higher is better. We ingest these ratings; we do not run the votes and we do not run our own evaluations.

⇩
The Known Good
Text to Video Arena — full ranking
48 models rated 1,235,424 votes countedRatings captured 8 Oct 2026 Source: Arena
# Model Creator Elo 95% CI Votes Known Good Index
1 gemini-omni-1.1-flash Google 1,516 ±15 1,784 —
2 gemini-omni-flash Google 1,513 ±9 26,576 —
3 flux-3-video Black Forest Labs 1,493 ±17 1,302 —
4 grok-imagine-video-1.5-agent xAI 1,492 ±18 1,218 —
5 dreamina-seedance-2.0-720p ByteDance 1,479 ±8 56,318 —
6 wan3.0 Alibaba 1,476 ±13 2,598 —
7 dreamina-seedance-2.5-720p ByteDance 1,474 ±9 8,001 —
8 minimax-h3 MiniMax 1,460 ±9 11,417 —
9 muse-video Meta 1,456 ±15 2,188 —
10 happyhorse-1.0 aorizon 1,427 ±13 22,264 —
11 sora-2-pro OpenAI 1,368 ±7 54,167 —
12 veo-3.1-audio Google 1,364 ±14 13,741 —
13 veo-3.1-audio-1080p Google 1,362 ±10 25,076 —
14 veo-3.1-fast-audio Google 1,362 ±10 39,484 —
15 veo-3.1-fast-audio-1080p Google 1,358 ±10 25,870 —
16 veo-3-fast-audio Google 1,348 ±11 25,258 —
17 sora-2 OpenAI 1,343 ±6 71,947 —
18 grok-imagine-video-720p xAI 1,342 ±6 165,462 —
19 veo-3-audio Google 1,340 ±13 19,002 —
20 wan2.7-t2v wan 1,337 ±7 27,626 —
21 wan2.6-t2v Alibaba 1,327 ±7 54,050 —
22 seedance-v1.5-pro ByteDance 1,256 ±7 76,171 —
23 veo-3 Google 1,254 ±11 15,005 —
24 veo-3-fast Google 1,248 ±12 15,283 —
25 wan2.5-t2v-preview Alibaba 1,245 ±9 36,378 —
26 pixverse-v5.6 Unknown 1,240 ±11 32,434 —
27 runway-gen-4.5 Runway 1,225 ±8 48,127 —
28 kling-2.5-turbo-1080p Kuaishou 1,220 ±17 2,111 —
29 kling-2.6-pro Kuaishou 1,216 ±7 73,362 —
30 p-video Unknown 1,207 ±16 7,079 —
31 ray-3 Luma AI 1,206 ±22 1,136 —
32 hailuo-2.3 MiniMax 1,206 ±6 89,138 —
33 kling-o1-pro Kuaishou 1,205 ±27 1,194 —
34 hailuo-02-pro MiniMax 1,198 ±13 9,399 —
35 seedance-v1-pro ByteDance 1,191 ±11 12,164 —
36 hailuo-02-standard MiniMax 1,181 ±12 9,379 —
37 kandinsky-5.0-t2v-pro kandinsky 1,175 ±21 2,019 —
38 hunyuan-video-1.5 Tencent 1,169 ±16 4,292 —
39 veo-2 Google 1,164 ±16 6,531 —
40 kling-v2.1-master Kuaishou 1,163 ±10 14,104 —
41 ltx-2-19b Unknown 1,154 ±8 75,596 —
42 wan-v2.2-a14b Alibaba 1,132 ±15 10,458 —
43 seedance-v1-lite ByteDance 1,113 ±10 16,253 —
44 kandinsky-5.0-t2v-lite kandinsky 1,113 ±18 1,474 —
45 sora OpenAI 1,069 ±16 4,082 —
46 ray2 Luma AI 1,065 ±17 5,250 —
47 pika-v2.2 Pika 1,009 ±15 5,763 —
48 mochi-v1 genmo 1,007 ±17 5,893 —
The Known Good
Image to Video Arena — full ranking
49 models rated 3,520,195 votes countedRatings captured 8 Oct 2026 Source: Arena
# Model Creator Elo 95% CI Votes Known Good Index
1 minimax-h3 MiniMax 1,495 ±5 57,112 —
2 gemini-omni-1.1-flash Google 1,488 ±11 3,734 —
3 wan3.0 Alibaba 1,480 ±11 3,442 —
4 dreamina-seedance-2.5-720p ByteDance 1,477 ±7 15,729 —
5 dreamina-seedance-2.0-720p ByteDance 1,475 ±7 121,427 —
3 grok-imagine-video-1.5-preview-720p xAI 1,466 ±5 44,400 —
6 gemini-omni-flash Google 1,465 ±6 87,155 —
7 hidream-o1-video-1.0 hidream 1,456 ±8 6,488 —
8 grok-imagine-video-1.5-720p xAI 1,456 ±4 137,459 —
9 flux-3-video-20260811 Black Forest Labs 1,449 ±5 37,042 —
10 happyhorse-1.0 aorizon 1,442 ±10 70,640 —
11 wan2.7-i2v wan 1,428 ±5 85,521 —
12 grok-imagine-video-720p xAI 1,415 ±4 554,050 —
13 veo-3.1-audio Google 1,398 ±10 25,116 —
14 veo-3.1-audio-1080p Google 1,390 ±9 53,089 —
15 veo-3.1-fast-audio Google 1,385 ±9 99,804 —
16 grok-imagine-video-480p xAI 1,385 ±8 19,429 —
17 veo-3.1-fast-audio-1080p Google 1,372 ±9 54,380 —
18 vidu-q3-pro shengshu 1,363 ±9 36,679 —
19 kling-v3-pro Kuaishou 1,354 ±6 206,221 —
20 veo-3-audio Google 1,331 ±12 32,367 —
21 veo-3-fast-audio Google 1,326 ±10 41,194 —
22 wan2.5-i2v-preview Alibaba 1,321 ±10 16,907 —
23 wan2.6-i2v Alibaba 1,310 ±7 121,082 —
24 seedance-v1.5-pro ByteDance 1,307 ±7 245,206 —
25 pixverse-v5.6 Unknown 1,299 ±7 126,710 —
26 kling-2.6-pro Kuaishou 1,294 ±8 202,113 —
27 kling-2.5-turbo-1080p Kuaishou 1,276 ±13 3,795 —
28 seedance-v1-pro ByteDance 1,273 ±8 34,019 —
29 hailuo-2.3 MiniMax 1,262 ±5 405,786 —
30 veo-3 Google 1,258 ±10 26,081 —
31 veo-3-fast Google 1,257 ±10 26,272 —
32 p-video Unknown 1,244 ±16 23,364 —
33 vidu-q2-turbo shengshu 1,244 ±17 2,509 —
34 kling-v2.1-master Kuaishou 1,235 ±8 29,824 —
35 hailuo-02-pro MiniMax 1,229 ±11 21,743 —
36 kling-v2.1-standard Kuaishou 1,229 ±8 29,957 —
37 ray-3 Luma AI 1,226 ±19 1,585 —
38 hailuo-02-standard MiniMax 1,224 ±10 21,785 —
39 vidu-q2-pro shengshu 1,223 ±17 2,614 —
40 hunyuan-video-1.5 Tencent 1,198 ±16 5,462 —
41 hailuo-02-fast MiniMax 1,194 ±11 22,519 —
42 seedance-v1-lite ByteDance 1,185 ±8 33,734 —
43 wan-v2.2-a14b Alibaba 1,170 ±10 27,054 —
44 veo-2 Google 1,166 ±16 10,303 —
45 ltx-2-19b Unknown 1,159 ±5 262,336 —
46 ray2 Luma AI 1,108 ±16 9,521 —
47 runway-gen4-turbo Runway 1,052 ±13 6,801 —
48 pika-v2.2 Pika 997 ±14 8,635 —
The Known Good
How to read Elo. A rating is only meaningful against the population that produced it: a model's number in one arena cannot be compared to its number in another, and a rating built on a few hundred votes moves far more than one built on tens of thousands — the 95% confidence interval is the honest guide to that. Elo measures which output a person preferred, not whether it was correct; for correctness see the evaluations and the Known Good Index, which does not include Elo. Ratings are ingested from Arena and are published under the source's own terms — see attribution.