Ethan Mollick@emollickEthan Mollick 用同一提示词测试多款模型生成虚构丘吉尔式嘲讽的能力，认为 GPT-5.6 Sol Pro 表现最佳，Fable 同样出色。Kimi 和 Gemini 则明显落后。此前他曾在类似测试中判定 Claude 获胜。
"Generate a fake， but believable， witty Churchill insult at a party and explain the context. It should be very clever and original"
This time， I think GPT 5.6 Sol Pro wins， but Fable is good too， and you could argue for it taking the prize. Kimi &； Gemini miss by a mile.
Ethan Mollick@emollick · XEthan Mollick 用同一提示词测试多款模型生成虚构丘吉尔式嘲讽的能力，认为 GPT-5.6 Sol Pro 表现最佳，Fable 同样出色。Kimi 和 Gemini 则明显落后。此前他曾在类似测试中判定 Claude 获胜。
"Generate a fake， but believable， witty Churchill insult at a party and explain the context. It should be very clever and original"
This time， I think GPT 5.6 Sol Pro wins， but Fable is good too， and you could argue for it taking the prize. Kimi &； Gemini miss by a mile.