Code2Video-Compass - V2V - ES: leaderboard
Code2Video-Compass (2026):347fixed V2Vtasks;15models generate code in one API call with provider-default reasoning, no execution feedback or repair. Failures score zero on quality metrics. V2V GPT/Claude receive4FPSframes, others native video at4FPS. Execution, image/video similarity and Gemini3.8Flash rubric scores remain separate; runtime tokens and average ranks omitted. Published ES Score.
Metric: Published ES Score. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 0.97 | #4 |
| 2 | Claude Sonnet 5.5 | 0.96 | #11 |
| 3 | Claude Haiku 5.5 | 0.93 | #40 |
| 4 | Gemini 3.8 Flash | 0.93 | #24 |
| 5 | GPT-6 Luna | 0.91 | #59 |
| 6 | MiMo-V2.6-Pro | 0.88 | #38 |
| 7 | GPT-6 Astra | 0.85 | #6 |
| 8 | GPT-6.1 Sol | 0.85 | #7 |
| 9 | DeepSeek V4.1 Flash | 0.82 | #35 |
| 10 | GLM-5.3 Flash | 0.78 | #71 |
| 11 | Kimi K3 | 0.76 | #30 |
| 12 | Qwen 3.8 Flash | 0.71 | #55 |
| 13 | Qwen 3.8 27B | 0.71 | #111 |
| 14 | Qwen 3.8 Max | 0.7 | #31 |
| 15 | MiniMax-M3 | 0.69 | #142 |
No result here: #8 Gemini 4 Argon, #9 Claude Fable 5.1, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=code2video-compass-v2v-es · How It Works · Data refreshed daily, snapshot 2026-10-22.