# Code2Video > HeyGen's Code2Video tests whether a model can turn a detailed creative brief into a finished motion-graphics video by writing code. Canonical page: https://benchlm.ai/benchmarks/code2video - Category: [Agentic](/agentic) - Last updated: Latest evaluation October 22, 2026 Evaluation results published by [HeyGen](https://www.kaggle.com/benchmarks/heygen/code2video). undefined A system receives a creative brief and a video environment built on Hyperframes, and must render a sequence that follows the brief: composition, typography, colour, timing, animation and transitions. The benchmark measures how closely the result executes the brief against a human-made reference, not whether the video is subjectively good. Kaggle publishes a relative rating with an interval and a Raw Score percentage for each model. The rating is relative to this pool of models and is not a percentage. Results are tied to the Hyperframes environment. The Code2Video Arena table on this page is a separate human-vote board and the two are not interchangeable. A rating gap smaller than the two rows' intervals is not a reliable difference. - [Kaggle leaderboard and Apache 2.0 declaration](https://www.kaggle.com/benchmarks/heygen/code2video) - [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/heygen/code2video/leaderboard) ## About Code2Video - Year: 2026 - Tasks: Creative briefs rendered as motion-graphics video - Format: Relative rating plus a raw score against human references - Difficulty: Code-driven motion design A system receives a creative brief and a video environment built on Hyperframes, and must render a sequence that follows the brief: composition, typography, colour, timing, animation and transitions. The benchmark measures how closely the result executes the brief against a human-made reference, not whether the video is subjectively good. Kaggle publishes a relative rating with an interval and a Raw Score percentage for each model. These results are display-only and do not enter overall or category rankings. Code2Video is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula. ## Leaderboard (19 source rows) | Rank | Model | Configuration | Creator | Score | |------|-------|---------------|---------|-------| | 1 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/heygen/code2video) | ±9; Raw Score 33.5%; Evaluated 2026-10-22 | — | 1585 | | 2 | [GPT-5.5](https://www.kaggle.com/benchmarks/heygen/code2video) | ±12; Raw Score 34.3%; Evaluated 2026-10-22 | — | 1571 | | 3 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/heygen/code2video) | ±10; Raw Score 28.9%; Evaluated 2026-10-22 | — | 1565 | | 4 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/heygen/code2video) | ±10; Raw Score 23.3%; Evaluated 2026-10-22 | — | 1548 | | 5 | [GPT-6 Sol](https://www.kaggle.com/benchmarks/heygen/code2video) | ±10; Raw Score 25.1%; Evaluated 2026-10-22 | — | 1546 | | 6 | [Claude Opus 5](https://www.kaggle.com/benchmarks/heygen/code2video) | ±10; Raw Score 25.7%; Evaluated 2026-10-22 | — | 1543 | | 7 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/heygen/code2video) | ±14; Raw Score 30.9%; Evaluated 2026-10-22 | — | 1539 | | 8 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/heygen/code2video) | ±8; Raw Score 19.6%; Evaluated 2026-10-22 | — | 1536 | | 9 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/heygen/code2video) | ±11; Raw Score 20.7%; Evaluated 2026-10-22 | — | 1533 | | 10 | [GLM-5.3](https://www.kaggle.com/benchmarks/heygen/code2video) | ±12; Raw Score 14.4%; Evaluated 2026-10-22 | — | 1496 | | 11 | [Kimi K3](https://www.kaggle.com/benchmarks/heygen/code2video) | ±11; Raw Score 10.4%; Evaluated 2026-10-22 | — | 1481 | | 12 | [Gemini 3.7 Flash](https://www.kaggle.com/benchmarks/heygen/code2video) | ±13; Raw Score 11.8%; Evaluated 2026-10-22 | — | 1477 | | 13 | [Deepseek V4 Flash 0731](https://www.kaggle.com/benchmarks/heygen/code2video) | ±11; Raw Score 9.4%; Evaluated 2026-10-22 | — | 1472 | | 14 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/heygen/code2video) | ±11; Raw Score 8.0%; Evaluated 2026-10-22 | — | 1469 | | 15 | [GLM-5.3-Flash](https://www.kaggle.com/benchmarks/heygen/code2video) | ±14; Raw Score 8.9%; Evaluated 2026-10-22 | — | 1467 | | 16 | [Gemini 3.1 Pro Preview](https://www.kaggle.com/benchmarks/heygen/code2video) | ±13; Raw Score 8.3%; Evaluated 2026-10-22 | — | 1454 | | 17 | [Grok 4.6](https://www.kaggle.com/benchmarks/heygen/code2video) | ±10; Raw Score 6.9%; Evaluated 2026-10-22 | — | 1450 | | 18 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/heygen/code2video) | ±13; Raw Score 6.6%; Evaluated 2026-10-22 | — | 1440 | | 19 | [Deepseek V4 Pro](https://www.kaggle.com/benchmarks/heygen/code2video) | ±16; Raw Score 3.9%; Evaluated 2026-10-22 | — | 1387 | ## Code2Video Arena Evaluation results published by [HeyGen](https://www.kaggle.com/benchmarks/heygen/code2video-arena). Source snapshot: Latest evaluation November 12, 2026. Ratings are shown as published, rounded to whole points. The vote count, interval and reasoning setting stay on each row. Missing results are not zero. - [Kaggle arena leaderboard](https://www.kaggle.com/benchmarks/heygen/code2video-arena) - [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/heygen/code2video-arena/leaderboard) | Source model | Configuration | Arena rating | |---|---|---| | [Gemini 4 Carbon](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 93 votes; ±116; Evaluated 2026-11-12 | 1599 | | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 713 votes; ±98; Evaluated 2026-11-12 | 1593 | | [GPT-6 Astra](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 690 votes; ±98; Evaluated 2026-11-12 | 1556 | | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 734 votes; ±98; Evaluated 2026-11-12 | 1548 | | [Claude Sonnet 5.5](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 737 votes; ±97; Evaluated 2026-11-12 | 1542 | | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 706 votes; ±98; Evaluated 2026-11-12 | 1526 | | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 707 votes; ±98; Evaluated 2026-11-12 | 1512 | | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | Xhigh Reasoning; 597 votes; ±98; Evaluated 2026-11-12 | 1476 | | [Claude Haiku 5.5](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 712 votes; ±98; Evaluated 2026-11-12 | 1475 | | [GLM-5.3](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 742 votes; ±97; Evaluated 2026-11-12 | 1449 | | [Kimi K3](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 705 votes; ±98; Evaluated 2026-11-12 | 1433 | | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 729 votes; ±98; Evaluated 2026-11-12 | 1413 | | [GLM-5.3-Flash](https://www.kaggle.com/benchmarks/heygen/code2video-arena) | High Reasoning; 727 votes; ±98; Evaluated 2026-11-12 | 1377 | ## FAQ ### What does Code2Video measure? HeyGen's Code2Video tests whether a model can turn a detailed creative brief into a finished motion-graphics video by writing code. ### Which source row has the highest reported Code2Video value? Claude Opus 5.5 has the highest reported Code2Video value at 1585. A rating gap smaller than the two rows' intervals is not a reliable difference. ### How many models are evaluated on Code2Video? The Latest evaluation October 22, 2026 contains 19 AI models. ### Does Code2Video affect BenchLM's overall score? Not directly. Code2Video is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.