Skip to content
Instruction

IFEval

Instruction Following Evaluation — precision in following instructions.

7 models published a score
# Model Company Score
1 Qwen3.7-Max Alibaba 94.3
2 Nova Pro Amazon 92.1
3 Claude Opus 4.5 Anthropic 92.0
4 Command A Cohere 90.9
5 GPT-5.2 OpenAI 89.4
6 AFM Server Apple 89.1
7 AFM On-Device Apple 85.1