Fig. 04 · Text benchmarkn = 8
Riddles, Slightly Off score
Chat models. Scores from 0 to 100. Higher is better.
A boy and his father crash. The surgeon, who is the boy's father, says "I can't operate, he's my son." How is this possible?
- Claude Opus 5.5 Claude Opus 5.5 Anthropic Riddles, Slightly Off score: 72
- DeepSeek V4.1 Flash DeepSeek V4.1 Flash DeepSeek Riddles, Slightly Off score: 67
- Claude Sonnet 5 Claude Sonnet 5 Anthropic Riddles, Slightly Off score: 61
- GPT-6 Astra GPT-6 Astra OpenAI Riddles, Slightly Off score: 58
- Qwen3.8 Max Qwen3.8 Max Alibaba Riddles, Slightly Off score: 49
- Gemini 3.8 Flash Gemini 3.8 Flash Google Riddles, Slightly Off score: 44
- Grok 4.7 Grok 4.7 xAI Riddles, Slightly Off score: 40
- GPT-6 Luna GPT-6 Luna OpenAI Riddles, Slightly Off score: 31
- OpenAI
- Anthropic
- DeepSeek
- xAI
- Alibaba