A-Fantasia Cube (Valid Attempts with Retries)
Games · 2026-09-30
A-Fantasia cube-rotation error among valid responses under the retry protocol. Six distinct colors and one to three quarter-turns; latest run with at least 80 valid items. Up to five retries for unscorable responses; denominator is not published.
Top models (lower is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 47.0 |
| Opus 4.6 | 53.0 |
| Opus 4.8 | 57.0 |
| Kimi K2 Instruct | 62.0 |
| Qwen3 Max (rolling alias) | 62.0 |
| GPT-5.5 | 63.0 |
| GPT-5.6 Sol | 63.0 |
| Kimi K2.6 | 64.0 |
| Gemini 1.5 Pro (source unspecified) | 64.0 |
| DeepSeek-V3-0324 | 65.1 |
| Qwen3.7-Plus (source unspecified) | 66.0 |
| Gemini 1.5 Flash (source unspecified) | 66.0 |
| GLM-5.1 | 67.0 |
| Opus 4.5 | 68.0 |
| GPT-5.4 | 68.0 |
| Claude 3.7 Sonnet | 68.0 |
| Gemini 2.0 Flash | 68.0 |
| Haiku 4.5 | 68.0 |
| DeepSeek V4.1 Flash | 68.0 |
| Llama 3.1 405B Instruct | 68.0 |
| DeepSeek-V3.2-Exp | 68.0 |
| Claude 3.5 Sonnet (Oct 2024) | 69.0 |
| Qwen3.6 Plus (2026-04-02) | 69.0 |
| Opus 4 | 69.1 |
| GLM-5 | 69.4 |
| Mistral Large 4 Preview | 70.0 |
| Sonnet 4 | 71.0 |
| DeepSeek-V3.1 | 71.0 |
| Opus 4.1 | 72.0 |
| Sonnet 4.5 | 72.0 |
| GLM-5.2 | 72.0 |
| Qwen3.8 Flash | 72.0 |
| MiniMax M3 | 72.0 |
| Sonnet 4.6 | 73.0 |
| GPT-5.6 Luna | 73.0 |
| Nemotron 3 Ultra 550B A55B | 73.0 |
| Gemini 2.5 Flash-Lite | 73.6 |
| Grok 4.20 | 73.7 |
| GPT-4o (source unspecified) | 74.0 |
| Opus 3 | 74.0 |