Benchmark Almanac

Code2Video Arena

Gemini 4 Carbon 1,599 leads since October 2026
Not in model cards

Models create videos through code. Pairwise votes determine the published Arena rating.

The official API publishes an Arena rating, confidence interval and vote count. Voter identity requires confirmation from the board description.

Kind
Video generation
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
Gemini 4 Carbon #2 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
13
Models scored on its own leaderboard

Gemini 4 Carbon leads with 1,599

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.

13 models. Scroll sideways for the rest. Bars start at 1,350.

  1. 1,599 Gemini 4 Carbon
  2. 1,591 Claude Opus 5.5
  3. 1,558 GPT-6 Astra
  4. 1,547 Gemini 4 Argon
  5. 1,542 Claude Sonnet 5.5
  6. 1,527 Claude Fable 5.1
  7. 1,511 GPT-6.1 Sol
  8. 1,479 Claude Haiku 5.5
  9. 1,475 Qwen 3.8 Max
  10. 1,449 GLM-5.3
  11. 1,433 Kimi K3
  12. 1,413 Gemini 3.8 Flash
  13. 1,377 GLM-5.3-Flash

Bars start at 1,350.

  1. 1 Gemini 4 Carbon Gemini 4 Carbon High Reasoning 1,599
  2. 2 Claude Opus 5.5 Claude Opus 5.5 High Reasoning 1,591
  3. 3 GPT-6 Astra GPT-6 Astra High Reasoning 1,558
  4. 4 Gemini 4 Argon Gemini 4 Argon High Reasoning 1,547
  5. 5 Claude Sonnet 5.5 Claude Sonnet 5.5 High Reasoning 1,542
  6. 6 Claude Fable 5.1 Claude Fable 5.1 High Reasoning 1,527
  7. 7 GPT-6.1 Sol GPT-6.1 Sol High Reasoning 1,511
  8. 8 Claude Haiku 5.5 Claude Haiku 5.5 High Reasoning 1,479
  9. 9 Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,475
  10. 10 GLM-5.3 GLM-5.3 High Reasoning 1,449
  11. 11 Kimi K3 Kimi K3 High Reasoning 1,433
  12. 12 Gemini 3.8 Flash Gemini 3.8 Flash High Reasoning 1,413
  13. 13 GLM-5.3-Flash GLM-5.3-Flash High Reasoning 1,377

Source: Official Code2Video Arena leaderboard

#ModelScoreSettingDateSource
1 Gemini 4 Carbon 1,599 Gemini 4 Carbon High Reasoning Oct 2026 Official leaderboard
2 Claude Opus 5.5 1,591 Claude Opus 5.5 High Reasoning Sep 2026 Official leaderboard
3 GPT-6 Astra 1,558 GPT-6 Astra High Reasoning Sep 2026 Official leaderboard
4 Gemini 4 Argon 1,547 Gemini 4 Argon High Reasoning Sep 2026 Official leaderboard
5 Claude Sonnet 5.5 1,542 Claude Sonnet 5.5 High Reasoning Sep 2026 Official leaderboard
6 Claude Fable 5.1 1,527 Claude Fable 5.1 High Reasoning Sep 2026 Official leaderboard
7 GPT-6.1 Sol 1,511 GPT-6.1 Sol High Reasoning Sep 2026 Official leaderboard
8 Claude Haiku 5.5 1,479 Claude Haiku 5.5 High Reasoning Oct 2026 Official leaderboard
9 Qwen 3.8 Max 1,475 Qwen 3.8 Max Xhigh Reasoning Aug 2026 Official leaderboard
10 GLM-5.3 1,449 GLM-5.3 High Reasoning Aug 2026 Official leaderboard
11 Kimi K3 1,433 Kimi K3 High Reasoning Jul 2026 Official leaderboard
12 Gemini 3.8 Flash 1,413 Gemini 3.8 Flash High Reasoning Sep 2026 Official leaderboard
13 GLM-5.3-Flash 1,377 GLM-5.3-Flash High Reasoning Aug 2026 Official leaderboard

6 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.

Moonshot AI Qwen Anthropic OpenAI Google DeepMind
Own leaderboard 6 leaders
Gemini 4 Carbon 1,599

Source: Official Code2Video Arena 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
1,350 1,400 1,450 1,500 1,550 1,600 2027 1,350 1,400 1,450 1,500 1,550 1,600 2027

Source: Official Code2Video Arena 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 232 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%