Arena: blind-test results
People vote on two anonymous outputs from one prompt. Models are ranked by rating; the 95% interval shows how settled each rating is.
- Updated Oct 19, 2026
- Ratings refresh hourly
- Methodology v3.3 →
Video models
Current top video models in the SpicyAPI arena: Seedance 2.0 (1094), Wan 3.0 (1091), and Seedance 2.0 Fast (1089). 35 video models are ranked as of October 19, 2026.
| # | Model | Rating | Votes | |
|---|---|---|---|---|
| 1 | Seedance 2.0 | 1094 | 95% interval 993–1251 | fewer than 50 votes |
| 2 | Wan 3.0 | 1091 | 95% interval 981–1188 | fewer than 50 votes |
| 3 | Seedance 2.0 Fast | 1089 | 95% interval 972–1213 | fewer than 50 votes |
| 4 | Seedance 2.0 Mini | 1087 | 95% interval 981–1191 | fewer than 50 votes |
| 5 | FLUX 3 | 1085 | 95% interval 889–1267 | fewer than 50 votes |
| 6 | Wan 3.0 Pro | 1072 | 95% interval 947–1217 | fewer than 50 votes |
| 7 | Seedance 2.5 | 1070 | 95% interval 960–1181 | fewer than 50 votes |
| 8 | Wan 3.0 Prime | 1069 | 95% interval 941–1169 | fewer than 50 votes |
| 9 | MiniMax H3 Max | 1055 | 95% interval 945–1164 | fewer than 50 votes |
| 10 | MiniMax H3 | 1053 | 95% interval 974–1158 | fewer than 50 votes |
| 11 | Kling 3.0 Turbo | 1052 | 95% interval 907–1189 | fewer than 50 votes |
| 12 | Wan 2.6 | 1032 | 95% interval 927–1154 | fewer than 50 votes |
| 13 | Vidu Q3 | 1031 | 95% interval 846–1191 | fewer than 50 votes |
| 14 | HappyHorse 1.1 | 1029 | 95% interval 932–1130 | fewer than 50 votes |
| 15–16 | Wan 2.7 Spicy | 1016 | 95% interval 851–1182 | fewer than 50 votes |
| 15–16 | Vidu Q3 Spicy | 1016 | 95% interval 859–1150 | fewer than 50 votes |
| 17 | LTX-2 19B | 1003 | 95% interval 857–1141 | fewer than 50 votes |
| 18 | Kling 3.0 | 988 | 95% interval 835–1162 | fewer than 50 votes |
| 19 | Wan 3.0 Pro Prime | 986 | 95% interval 821–1154 | fewer than 50 votes |
| 20–21 | Seedance 1.5 Pro Spicy | 984 | 95% interval 846–1129 | fewer than 50 votes |
| 20–21 | LTX 2.3 Spicy | 984 | 95% interval 802–1172 | fewer than 50 votes |
| 22 | Seedance 2.0 Fast Spicy | 982 | 95% interval 814–1120 | fewer than 50 votes |
| 23 | Seedance 2.0 Mini Spicy | 979 | 95% interval 846–1168 | fewer than 50 votes |
| 24 | Vidu Q3 Pro | 966 | 95% interval 813–1117 | fewer than 50 votes |
| 25 | Wan 2.6 Flash | 963 | 95% interval 829–1087 | fewer than 50 votes |
| 26 | Kling 2.5 Turbo | 950 | 95% interval 769–1133 | fewer than 50 votes |
| 27–28 | Wan 2.5 | 944 | 95% interval 844–1049 | fewer than 50 votes |
| 27–28 | LTX 2.5 | 944 | 95% interval 806–1088 | fewer than 50 votes |
| 29 | Wan 2.2 Spicy | 942 | 95% interval 806–1082 | fewer than 50 votes |
| 30 | Vidu Q3 Turbo | 941 | 95% interval 790–1073 | fewer than 50 votes |
| 31 | Kling O3 | 938 | 95% interval 771–1121 | fewer than 50 votes |
| 32 | Seedance 1.5 Pro | 932 | 95% interval 843–1042 | fewer than 50 votes |
| 33 | Kling 2.6 | 910 | 95% interval 766–1075 | fewer than 50 votes |
| 34 | Kling 2.1 | 879 | 95% interval 735–1069 | fewer than 50 votes |
| 35 | Wan 2.2 | 846 | 95% interval 711–995 | fewer than 50 votes |
Waiting for first votes (9)
| # | Model | Rating | 95% interval | Votes |
|---|---|---|---|---|
| — | Seedance 2.5 Spicy | — | — | — |
| — | Wan 3.0 Spicy | — | — | — |
| — | MiniMax H3 Spicy | — | — | — |
| — | Wan 3.0 Prime Spicy | — | — | — |
| — | Vidu Q4 Preview | — | — | — |
| — | MiniMax H3 Singularity LoRA | — | — | — |
| — | Seedance 2.0 Spicy | — | — | — |
| — | Wan 2.6 Spicy | — | — | — |
| — | HunyuanVideo 1.5 | — | — | — |
Image models
Current top image models in the SpicyAPI arena: GPT Image 2.5 Flare (1202), GPT Image 2.5 Sunburst (1187), and GPT Image 2 (1144). 37 image models are ranked as of October 19, 2026.
| # | Model | Rating | Votes | |
|---|---|---|---|---|
| 1 | GPT Image 2.5 Flare | 1202 | 95% interval 1034–1353 | fewer than 50 votes |
| 2 | GPT Image 2.5 Sunburst | 1187 | 95% interval 1059–1334 | fewer than 50 votes |
| 3 | GPT Image 2 | 1144 | 95% interval 1005–1290 | fewer than 50 votes |
| 4 | Nano Banana 2 | 1124 | 95% interval 988–1283 | fewer than 50 votes |
| 5 | Qwen Image 3.0 | 1071 | 95% interval 959–1187 | fewer than 50 votes |
| 6 | Jib Mix Qwen | 1045 | 95% interval 898–1215 | fewer than 50 votes |
| 7–8 | Qwen Image 3.0 Pro | 1039 | 95% interval 885–1123 | fewer than 50 votes |
| 7–8 | Nano Banana Pro | 1039 | 95% interval 879–1169 | fewer than 50 votes |
| 9 | Krea 2 Large | 1038 | 95% interval 940–1157 | fewer than 50 votes |
| 10 | Seedream 5.0 Lite | 1028 | 95% interval 928–1137 | fewer than 50 votes |
| 11 | Seedream 4.0 | 1021 | 95% interval 904–1131 | fewer than 50 votes |
| 12 | Qwen Image Edit Spicy | 1018 | 95% interval 847–1184 | fewer than 50 votes |
| 13–14 | Seedream 5.0 Flash | 1017 | 95% interval 859–1164 | fewer than 50 votes |
| 13–14 | FLUX.1 Dev LoRA | 1017 | 95% interval 917–1128 | fewer than 50 votes |
| 15 | Nano Banana 2.1 | 1012 | 95% interval 875–1147 | fewer than 50 votes |
| 16 | Z-Image Spicy | 1009 | 95% interval 886–1149 | fewer than 50 votes |
| 17 | Seedream 5.0 Pro | 999 | 95% interval 876–1096 | fewer than 50 votes |
| 18 | Z-Image Base LoRA | 998 | 95% interval 863–1144 | fewer than 50 votes |
| 19 | Z-Image Spicy Pro | 989 | 95% interval 872–1127 | fewer than 50 votes |
| 20 | Krea 2 Medium Turbo | 985 | 95% interval 863–1095 | fewer than 50 votes |
| 21 | Wan 2.7 Pro | 982 | 95% interval 890–1099 | fewer than 50 votes |
| 22 | FLUX.2 Max | 971 | 95% interval 810–1088 | fewer than 50 votes |
| 23 | Qwen Image 2 | 969 | 95% interval 880–1072 | fewer than 50 votes |
| 24 | Krea 2 Medium | 968 | 95% interval 859–1089 | fewer than 50 votes |
| 25 | FLUX.2 Flex | 965 | 95% interval 808–1114 | fewer than 50 votes |
| 26 | Anima Turbo | 962 | 95% interval 816–1113 | fewer than 50 votes |
| 27 | Wan 2.7 | 959 | 95% interval 855–1056 | fewer than 50 votes |
| 28 | Qwen Image 2.1 | 957 | 95% interval 833–1052 | fewer than 50 votes |
| 29 | Qwen Image 2512 LoRA | 955 | 95% interval 861–1050 | fewer than 50 votes |
| 30 | Z-Image | 948 | 95% interval 844–1052 | fewer than 50 votes |
| 31 | FLUX.2 Pro | 947 | 95% interval 815–1087 | fewer than 50 votes |
| 32 | FLUX.2 Dev | 935 | 95% interval 786–1060 | fewer than 50 votes |
| 33 | Neta Lumina | 930 | 95% interval 781–1084 | fewer than 50 votes |
| 34 | MiniMax H3 Image LoRA | 922 | 95% interval 810–1036 | fewer than 50 votes |
| 35 | FLUX.2 Klein 9B | 884 | 95% interval 690–1040 | fewer than 50 votes |
| 36 | FLUX.2 Klein 4B | 883 | 95% interval 731–1051 | fewer than 50 votes |
| 37 | Prefect Pony XL | 881 | 95% interval 749–1023 | fewer than 50 votes |
