AI Battle > Rankings > Arena Elo
null by null leads the Arena Elo ranking with a score of 1206. The ranking covers 85 evaluated image-to-video from a public dataset that AI Battle re-checks daily.
Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 85 entries shown.
| # | Entry | Creator | Value | Δ vs #1 |
|---|---|---|---|---|
| 1 | Minimax H3 Max (post-trained by fal) | 1206 | 0.0% | |
| 2 | Dreamina Seedance 2.0 720p | 1346 | 11.6% | |
| 3 | MiniMax H3 | 1352 | 12.1% | |
| 4 | HiDream-O1-Video | 1186 | -1.7% | |
| 5 | Gemini Omni Flash | 1365 | 13.1% | |
| 6 | Wan 3.0 | 1359 | 12.7% | |
| 7 | grok-imagine-video-1.5 | 1328 | 10.1% | |
| 8 | HappyHorse-1.1 | 1303 | 8.0% | |
| 9 | MAGI-2 Preview | 1101 | -8.7% | |
| 10 | HappyHorse-1.0 | 1291 | 7.1% | |
| 11 | Veo 3.1 | 1248 | 3.4% | |
| 12 | Wan 2.7 | 1274 | 5.6% | |
| 13 | SkyReels V4 | 1289 | 6.8% | |
| 14 | grok-imagine-video | 1321 | 9.5% | |
| 15 | Kling 3.0 1080p (Pro) | 1282 | 6.3% | |
| 16 | Veo 3.1 Fast | 1262 | 4.7% | |
| 17 | Kling 3.0 720p (Standard) | 1272 | 5.4% | |
| 18 | Veo 3.1 Lite | 1246 | 3.3% | |
| 19 | PixVerse V6 | 1327 | 10.0% | |
| 20 | Kling 3.0 Omni 1080p (Pro) | 1283 | 6.4% | |
| 21 | Vidu Q3 Pro | 1278 | 5.9% | |
| 22 | Kling 3.0 Omni 720p (Standard) | 1268 | 5.2% | |
| 23 | LTX-2.5 Fast | 1209 | 0.2% | |
| 24 | Vidu Q3 Turbo | 1220 | 1.2% | |
| 25 | Agnes-Video-2.5 | 1040 | -13.8% | |
| 26 | LTX-2.5 Pro | 1190 | -1.3% | |
| 27 | Kling 2.6 Pro (January) | 1267 | 5.0% | |
| 28 | Seedance 1.5 pro | 1246 | 3.3% | |
| 29 | PixVerse V5.6 (January) | 1243 | 3.1% | |
| 30 | PixVerse V5.6 | 1273 | 5.5% | |
| 31 | LTX-2.3 Pro | 1157 | -4.1% | |
| 32 | LTX-2.3 Fast | 1165 | -3.4% | |
| 33 | LTX-2 Fast | 1185 | -1.7% | |
| 34 | Agnes-Video-V2.0 | 1136 | -5.8% | |
| 35 | Wan 2.6 | 1215 | 0.7% | |
| 36 | LTX-2 Pro | 1191 | -1.3% | |
| 37 | Bach 1.0 Pro | 1364 | 13.1% | |
| 38 | Kling 2.5 Turbo 1080p | 1292 | 7.1% | |
| 39 | Kling 2.6 Standard (January) | 1294 | 7.3% | |
| 40 | Cosmos3-Super-Image2Video-4Step | 1264 | 4.8% | |
| 41 | PixVerse V5.5 | 1268 | 5.1% | |
| 42 | Runway Gen-4.5 | 1266 | 5.0% | |
| 43 | PixVerse V5 | 1263 | 4.7% | |
| 44 | Avenger 0.5 Pro | 1268 | 5.1% | |
| 45 | Kling 2.6 Pro (December) | 1256 | 4.1% | |
| 46 | Cosmos3-Super-Image2Video | 1244 | 3.2% | |
| 47 | Hailuo 2.3 Fast | 1245 | 3.2% | |
| 48 | Hailuo 2.3 | 1242 | 3.0% | |
| 49 | Hailuo 02 Standard | 1239 | 2.8% | |
| 50 | Hailuo 02 Pro | 1242 | 3.0% | |
| 51 | Avenger 0.5 | 1242 | 3.0% | |
| 52 | Wan 2.5 Preview | 1234 | 2.3% | |
| 53 | Seedance 1.0 | 1229 | 1.9% | |
| 54 | Veo 3 | 1224 | 1.5% | |
| 55 | Vidu Q2 Turbo | 1218 | 1.0% | |
| 56 | Vidu Q2 Pro | 1228 | 1.8% | |
| 57 | Ray 3 | 1222 | 1.3% | |
| 58 | Kling 2.1 Master | 1209 | 0.2% | |
| 59 | Hailuo 02 Fast | 1195 | -0.9% | |
| 60 | Pika 2.5 | 1195 | -0.9% | |
| 61 | Kling 2.1 Pro | 1183 | -1.9% | |
| 62 | Kling 2.0 | 1182 | -2.0% | |
| 63 | Kling 2.1 Standard | 1167 | -3.3% | |
| 64 | Vivago 2.0 | 1171 | -2.9% | |
| 65 | Midjourney V1 | 1164 | -3.5% | |
| 66 | Seedance 1.0 Mini | 1145 | -5.1% | |
| 67 | PixVerse V4.5 | 1137 | -5.8% | |
| 68 | Kling 1.6 Pro | 1130 | -6.3% | |
| 69 | HunyuanVideo-1.5 (Fal) | 1123 | -6.9% | |
| 70 | P-Video | 1126 | -6.7% | |
| 71 | Wan 2.2 A14B | 1109 | -8.1% | |
| 72 | Veo 2 | 1094 | -9.3% | |
| 73 | Runway Gen 4 | 1080 | -10.4% | |
| 74 | LTX Video v0.9.7 13B | 1037 | -14.0% | |
| 75 | I2V-01-Director | 1033 | -14.4% | |
| 76 | Vidu Q1 | 1023 | -15.2% | |
| 77 | Motion 2.0 | 1021 | -15.4% | |
| 78 | Marey | 1010 | -16.3% | |
| 79 | Wan 2.1 14B | 1000 | -17.1% | |
| 80 | Pika 2.2 | 992 | -17.7% | |
| 81 | Runway Gen 3 Alpha | 991 | -17.8% | |
| 82 | Runway Gen 3 Alpha Turbo | 992 | -17.7% | |
| 83 | Wan 2.2 5B | 992 | -17.7% | |
| 84 | Sora | 977 | -19.0% | |
| 85 | Hunyuan Video (Fal) | 919 | -23.8% |
Across the 85 numeric entries in this window the median is 1222 and the mean is 1196, so the typical entry sits 15.9 above the leader. The window spans 919 to 1365.
43 of 85 entries are at or above the median, and the top three hold 4% of the combined value — read it against the metric below, since a higher number is not "better" for every dataset.
The source dataset for this family does not publish a provider or creator label per entry, so AI Battle cannot group them: the table above is the complete published list. Where the dataset does carry a label (model, gateway and tool families do), this section names the creators and how many entries each holds.
This ranking carries the metrics
appearances, ciDelta, ciLower, ciUpper, elo, pricePerMinute, rank from the
Arena Elo dataset in the tab::video-image-to-video family. Units and the
direction of "better" are not declared by the source dataset, so AI Battle does not invent
them: values are shown exactly as published, and the ordering is the source dataset's own.
Rebuilt on from the
public dataset Arena Elo (family tab::video-image-to-video).
The source lists 85 entries and all 85 are shown here. AI Battle requests
the dataset's rows, keeps the ordering the source publishes, and computes only the statistics
on this page: median, mean, spread, the #1–#2 gap, the creator breakdown and the raw-data file.
Nothing on this page is generated text about the entries — the numbers come from the source.
Refresh cadence: every deploy re-pulls the dataset, so this page tracks the source's own update cycle. Corrections: see the methodology page.
Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/video-image-to-video-arena-elo.json. Free to reuse with attribution to AI Battle and the source dataset.
null by null currently leads the Arena Elo ranking with a score of 1206, the highest value in this dataset across Image-to-Video. AI Battle aggregates the dataset from its public source and re-checks it daily.
The Arena Elo ranking is rebuilt daily from the upstream public dataset. Scores are the source dataset's own published values, so positions track whatever that source last released — each ranking page names the dataset it comes from.
The top 3 are: 1. null (1206), 2. null (1346), 3. null (1352).