MineBench, a benchmark for evaluating AI models' ability to generate 3D structures, has released version 4.0. This update includes a community gallery for users to showcase and upvote custom prompts, and introduces A/B testing for private model checkpoints. Additionally, MineBench is now available on the iOS App Store. For a limited time, logged-in users can access unlimited generations with Gemini 3.7 Flash, a collaboration with Google Deepmind. AI
IMPACT Enhances AI model evaluation capabilities with new features for community engagement and private testing.
RANK_REASON This is a software release for a benchmarking tool, not a frontier model release.
- Claude Fable 5
- Claude Opus 4.6
- Claude Opus 4.7
- Claude Opus 4.8
- Claude Opus 5
- Gemini 3.7 Flash
- Google Deepmind
- GPT 5.4
- GPT 5.4-Pro
- GPT 5.5
- GPT-5.5 Pro
- GPT-5.6 Sol
- Kimi K2.5
- Kimi K2.6
- MineBench
- United States
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →