AA Code2Video-AA (Dataset 0.3.0): leaderboard

Artificial Analysis Code2Video-AA dataset 0.3.0: 114 design briefs (39 public, 75 private). One no-tool generation using HeyGen system prompt; HTML layout and GSAP animation rendered offline with HyperFrames 0.8.30, five-minute render limit. Anonymous pairwise Gemini 4 Argon judging at 8fps/high media resolution; independent Bradley-Terry fits on engagement, prompt intent, composition, temporal consistency and craft. Overall is the mean of five axis Elos, each anchored to GPT-5.5 (xhigh) at 1000. Render failures lose to successful renders and tie each other. Effort/default-fallback labels remain separate. Gemini 4 Argon is both a rated generator and the judge; these roles and shared axes are not independent replication. Metric: Mean axis Elo (GPT-5.5 xhigh anchor=1000).

Metric: Mean axis Elo (GPT-5.5 xhigh anchor=1000). Source: artificialanalysis.ai. Saturation forecast: Around January 2028. 27 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6 Astra (Max)1426.78#5 (GPT-6 Astra)
2GPT-6.1 Sol (Max)1369.3#6 (GPT-6.1 Sol)
3Gemini 4 Argon (High)1259.4#8 (Gemini 4 Argon)
4Claude Haiku 5.5 (Max)1192.35#41 (Claude Haiku 5.5)
5Grok 4.7 (xHigh)1126.6#27 (Grok 4.7)
6DeepSeek V4.1 Flash (Max)1053.11#38 (DeepSeek V4.1 Flash)
7MiMo-V2.6-Flash1051.56#75
8MiMo-V2.6-Pro1051.51#46
9Kimi K3 (Max)1041.34#34 (Kimi K3)
10GLM-5.3 (Max)1033.51#40 (GLM-5.3)
11GPT-6 Luna (Max)1029.65#60 (GPT-6 Luna)
12Qwen 3.8 Max (0902)1020.76#32
13Muse Spark 1.3 (Max)1018.78#30 (Muse Spark 1.3)
14GPT-5.5 (xHigh)1000#31 (GPT-5.5)
15Muse Wonder (Max)997.01#16 (Muse Wonder)

No result here: #3 Claude Opus 5.5, #9 Claude Fable 5.1, #10 GPT-6.1 Terra.

Interactive version: theaggregate.ai/benchmark?slug=aa-code2video-aa-dataset-0-3-0 · How It Works · Data refreshed daily, snapshot 2026-10-27.