Fig. 04 · Vision benchmarkn = 7
Five-Legged Dog score
Chat models. Scores from 0 to 100. Higher is better.
How many legs does this dog have? Reply with a number.
- GPT-6 Astra GPT-6 Astra OpenAI Five-Legged Dog score: 80
- Gemini 3.8 Flash Gemini 3.8 Flash Google Five-Legged Dog score: 74
- Claude Opus 5.5 Claude Opus 5.5 Anthropic Five-Legged Dog score: 64
- Claude Sonnet 5 Claude Sonnet 5 Anthropic Five-Legged Dog score: 57
- Qwen3.8 Max Qwen3.8 Max Alibaba Five-Legged Dog score: 53
- GPT-6 Luna GPT-6 Luna OpenAI Five-Legged Dog score: 49
- Grok 4.7 Grok 4.7 xAI Five-Legged Dog score: 38
DeepSeek V4.1 Flash can't see images, so they skip this one.
- OpenAI
- Anthropic
- DeepSeek
- xAI
- Alibaba