Code2Video-Compass - I2V - PF: leaderboard
Code2Video-Compass (2026):347fixed I2Vtasks;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 PF Score.
Metric: Published PF Score. Source: arxiv.org. Saturation forecast: Around January 2028. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 0.89 | #4 |
| 2 | Claude Sonnet 5.5 | 0.89 | #11 |
| 3 | Claude Haiku 5.5 | 0.86 | #40 |
| 4 | Gemini 3.8 Flash | 0.84 | #24 |
| 5 | GPT-6 Astra | 0.83 | #6 |
| 6 | GPT-6.1 Sol | 0.83 | #7 |
| 7 | GPT-6 Luna | 0.82 | #59 |
| 8 | MiMo-V2.6-Pro | 0.79 | #38 |
| 9 | Kimi K3 | 0.78 | #30 |
| 10 | DeepSeek V4.1 Flash | 0.75 | #35 |
| 11 | GLM-5.3 Flash | 0.7 | #71 |
| 12 | Qwen 3.8 Flash | 0.69 | #55 |
| 13 | Qwen 3.8 27B | 0.65 | #111 |
| 14 | Qwen 3.8 Max | 0.59 | #31 |
| 15 | MiniMax-M3 | 0.49 | #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-i2v-pf · How It Works · Data refreshed daily, snapshot 2026-10-22.