gemini-4POST
LisanBench 去掉编辑距离规则后:GPT 6 Astra 领先 Gemini 4 Argon
帖子引用 LisanBench 去掉编辑距离规则后的重排结果:GPT 6 Astra medium 第一、Gemini 4 Argon high 第二、GPT 6.1 Sol medium 第三,并称三者都确认存在循环问题。
Lisan al Gaib
@scaling017 天前收录原推发布于 2026.10.25
Lisan al Gaib @scaling01原推发布于 2026.10.25
it's good to know that OpenAI models are at least SOTA on a subtask of LisanBench: "When scoring the models without the edit-distance one rule (all the other rules still active) the ranking changes completely: 1. GPT 6 Astra medium: 56,140 (+659%) 2. Gemini 4 Argon high: 51,312 (+579%) 3. GPT 6.1 Sol medium: 49,887 (+731%)" ALL THREE CONFIRMED LOOPERS AT THE TOP 👀
这条是引用着另一条写的:「LisanBench 更新:Gemini 4 Argon 低推理档登顶非思考榜」
x.com/scaling01/status/2114065353663815782采集于 2026.10.25 09:53