Benchmarks · creative
Code2Video-AA
Code2Video-AA: AA's run of HeyGen's Code2Video Bench. Models turn 114 design briefs into short product and brand videos in HyperFrames HTML; Elo from blind pairwise votes.
21 models · 21 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Opus 5.5 max
More from this benchmark
5 published measuresScore vs any published measure5 measures: sub-scores, splits, counts
All results
21 rows| # | Model | Effort | Code2Video-AA |
|---|---|---|---|
| 1 | Opus 5.5 | max | 1536 ±26 |
| 2 | Sonnet 5.5 | max | 1443 ±24 |
| 3 | GPT-6 Astra | max | 1427 ±24 |
| 4 | GPT-6.1 Sol | max | 1369 ±23 |
| 5 | Fable 5.1 | max | 1325 ±22 |
| 6 | Gemini 4 Argon | high | 1259 ±22 |
| 7 | Haiku 5.5 | max | 1192 ±21 |
| 8 | Grok 4.7 | xhigh | 1127 ±20 |
| 9 | DeepSeek V4.1 Flash | max | 1053 ±20 |
| 10 | MiMo V2.6 Flash | 1052 ±20 | |
| 11 | MiMo V2.6 Pro | 1052 ±20 | |
| 12 | Kimi K3 | max | 1041 ±20 |
| 13 | GLM 5.3 | max | 1034 ±20 |
| 14 | GPT-6 Luna | max | 1030 ±20 |
| 15 | Muse Spark 1.3 | max | 1019 ±20 |
| 16 | GPT-5.5 | xhigh | 1000 ±0 |
| 17 | GLM 5.3 Flash | max | 975 ±20 |
| 18 | Qwen 3.8 27B | xhigh | 949 ±20 |
| 19 | Gemini 3.8 Flash | high | 899 ±20 |
| 20 | MiniMax M3 | 724 ±23 | |
| 21 | Inkling | xhigh | 467 ±28 |