VoxelCodeBench
Models write code to build and modify voxel scenes. The benchmark checks the constructed shapes and evaluates their appearance.
- Made by
- Yan Zheng and colleagues
- Released
- April 2026
- Kind
- Image generation and editing
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Subject
- Computer and information sciences, Arts
- Language
- English
- Interaction
- Single turn
- Environment
- Unreal Engine
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
GPT-5 leads with 87.9% among models released by September 2025
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5 87.9%
- 2 GPT-5 mini 80.4%
- 3 Claude Sonnet 4.5 80.4%
- 4 GPT-5 Chat 69.7%
- 5 Claude Opus 4 69.4%
- 6 Claude 3.5 Sonnet 66.9%
- 7 Claude 3 Opus 45.2%
- 8
Gemini 1.0 Pro 19.5%
Source: The VoxelCodeBench paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 | 87.9% | Aug 2025 | Official leaderboard | |
| 2 | GPT-5 mini | 80.4% | Aug 2025 | Official leaderboard | |
| 3 | Claude Sonnet 4.5 | 80.4% | Sep 2025 | Official leaderboard | |
| 4 | GPT-5 Chat | 69.7% | Aug 2025 | Official leaderboard | |
| 5 | Claude Opus 4 | 69.4% | May 2025 | Official leaderboard | |
| 6 | Claude 3.5 Sonnet | 66.9% | Jun 2024 | Official leaderboard | |
| 7 | Claude 3 Opus | 45.2% | Feb 2024 | Official leaderboard | |
| 8 | | 19.5% | Dec 2023 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The VoxelCodeBench paper
GPT-5 on the official leaderboard passed 85% in August 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official VoxelCodeBench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (8 entries).
- Pass Models scored 8 models we track.
- Note Newest score The newest came 14 months ago, in September 2025, for Claude Sonnet 4.5. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 (#71).
- Note Headroom Saturated. The best is 87.9%, past 85% since August 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 8 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.