Benchmark Almanac

DesignArena Code to Video

Claude Opus 5.5 1,341 leads since September 2026
Not in model cards

Agents write code that renders a video from a user prompt. Users compare the two videos and vote for the better one.

One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Video generation
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
29
Models scored on its own leaderboard

Claude Opus 5.5 leads with 1,341

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

29 models. Scroll sideways for the rest. Bars start at 800.

  1. 1,341 Claude Opus 5.5
  2. 1,318 Claude Sonnet 5.5
  3. 1,270 Kimi K3
  4. 1,268 GPT-6 Astra
  5. 1,247 Claude Opus 5
  6. 1,232 Kimi K3.1 Pro
  7. 1,216 MiniMax-M3
  8. 1,206 Muse Spark 1.3
  9. 1,199 MiniMax-M3.1-Flash
  10. 1,198 Gemini 3.7 Flash
  11. 1,192 GPT-6.1 Sol
  12. 1,189 Gemini 3.8 Flash
  13. 1,187 Claude Opus 4.8
  14. 1,148 Gemini 3.5 Flash
  15. 1,139 Grok 4.6
  16. 1,137 GPT-5.6 Sol
  17. 1,123 Grok 4.5
  18. 1,119 Gemini 3.1 Pro
  19. 1,112 GPT-6.1 Terra
  20. 1,110 Claude Opus 4.6
  21. 1,110 Grok 4.7
  22. 1,109 Claude Sonnet 5
  23. 1,106 Gemini 3.6 Flash
  24. 1,103 Muse Spark 1.2
  25. 1,090 GPT-6 Sol
  26. 1,078 Muse Spark 1.1
  27. 1,028 GPT-6 Luna
  28. 972 GPT-5.6 Terra
  29. 896 Grok 4.3

Bars start at 800.

  1. 1 Claude Opus 5.5 1,341
  2. 2 Claude Sonnet 5.5 1,318
  3. 3 Kimi K3 1,270
  4. 4 GPT-6 Astra xhigh 1,268
  5. 5 Claude Opus 5 1,247
  6. 6 Kimi K3.1 Pro 1,232
  7. 7 MiniMax-M3 1,216
  8. 8 Muse Spark 1.3 xhigh, max 1,206
  9. 9 MiniMax-M3.1-Flash 1,199
  10. 10 Gemini 3.7 Flash 1,198
  11. 11 GPT-6.1 Sol 1,192
  12. 12 Gemini 3.8 Flash 1,189
  13. 13 Claude Opus 4.8 1,187
  14. 14 Gemini 3.5 Flash 1,148
  15. 15 Grok 4.6 1,139
  16. 16 GPT-5.6 Sol medium, xhigh 1,137
  17. 17 Grok 4.5 1,123
  18. 18 Gemini 3.1 Pro 1,119
  19. 19 GPT-6.1 Terra 1,112
  20. 20 Claude Opus 4.6 1,110
  21. 21 Grok 4.7 1,110
  22. 22 Claude Sonnet 5 1,109
  23. 23 Gemini 3.6 Flash 1,106
  24. 24 Muse Spark 1.2 1,103
  25. 25 GPT-6 Sol 1,090
  26. 26 Muse Spark 1.1 1,078
  27. 27 GPT-6 Luna 1,028
  28. 28 GPT-5.6 Terra 972
  29. 29 Grok 4.3 896

Source: Official DesignArena Code to Video leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 1,341 Sep 2026 Official leaderboard
2 Claude Sonnet 5.5 1,318 Sep 2026 Official leaderboard
3 Kimi K3 1,270 Jul 2026 Official leaderboard
4 GPT-6 Astra 1,268 xhigh Sep 2026 Official leaderboard
5 Claude Opus 5 1,247 Jul 2026 Official leaderboard
6 Kimi K3.1 Pro 1,232 Oct 2026 Official leaderboard
7 MiniMax-M3 1,216 Jun 2026 Official leaderboard
8 Muse Spark 1.3 1,206 xhigh, max Sep 2026 Official leaderboard
9 MiniMax-M3.1-Flash 1,199 Oct 2026 Official leaderboard
10 Gemini 3.7 Flash 1,198 Aug 2026 Official leaderboard
11 GPT-6.1 Sol 1,192 Sep 2026 Official leaderboard
12 Gemini 3.8 Flash 1,189 Sep 2026 Official leaderboard
13 Claude Opus 4.8 1,187 May 2026 Official leaderboard
14 Gemini 3.5 Flash 1,148 May 2026 Official leaderboard
15 Grok 4.6 1,139 Aug 2026 Official leaderboard
16 GPT-5.6 Sol 1,137 medium, xhigh Jul 2026 Official leaderboard
17 Grok 4.5 1,123 Jul 2026 Official leaderboard
18 Gemini 3.1 Pro 1,119 Feb 2026 Official leaderboard
19 GPT-6.1 Terra 1,112 Oct 2026 Official leaderboard
20 Claude Opus 4.6 1,110 Feb 2026 Official leaderboard
21 Grok 4.7 1,110 Sep 2026 Official leaderboard
22 Claude Sonnet 5 1,109 Jun 2026 Official leaderboard
23 Gemini 3.6 Flash 1,106 Jul 2026 Official leaderboard
24 Muse Spark 1.2 1,103 Aug 2026 Official leaderboard
25 GPT-6 Sol 1,090 Sep 2026 Official leaderboard
26 Muse Spark 1.1 1,078 Jul 2026 Official leaderboard
27 GPT-6 Luna 1,028 Sep 2026 Official leaderboard
28 GPT-5.6 Terra 972 Jul 2026 Official leaderboard
29 Grok 4.3 896 Apr 2026 Official leaderboard

7 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic Google DeepMind MiniMax Moonshot AI
Own leaderboard 7 leaders
Claude Opus 5.5 1,341

Source: Official DesignArena Code to Video leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
800 1,000 1,200 1,400 2026 2027 800 1,000 1,200 1,400 2026 2027

Source: Official DesignArena Code to Video leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Audio and video

All 233 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%