Fig. 04 · Text benchmarkn = 8
Hot Takes score
Chat models. Scores from 0 to 100. Higher is better.
Is a hot dog a sandwich? Answer yes or no. One word.
- Grok 4.7 Grok 4.7 xAI Hot Takes score: 97
- DeepSeek V4.1 Flash DeepSeek V4.1 Flash DeepSeek Hot Takes score: 71
- GPT-6 Luna GPT-6 Luna OpenAI Hot Takes score: 68
- Qwen3.8 Max Qwen3.8 Max Alibaba Hot Takes score: 62
- Claude Sonnet 5 Claude Sonnet 5 Anthropic Hot Takes score: 60
- Claude Opus 5.5 Claude Opus 5.5 Anthropic Hot Takes score: 55
- GPT-6 Astra GPT-6 Astra OpenAI Hot Takes score: 47
- Gemini 3.8 Flash Gemini 3.8 Flash Google Hot Takes score: 38
- OpenAI
- Anthropic
- DeepSeek
- xAI
- Alibaba