gemini-4IMAGE
Gemini 4 Argon 在 RSI 指数排第 4,KSP Bench 不早停
评测称 Gemini 4 Argon 在 RSI 指数排第四,泛化能力极强、在 KSP Bench 上不出现平台期,与 Fable 5.1、GPT-6 Astra、Opus 5.5 同属能通关的少数模型。
spicylemonade
@spicey_lemonade28 天前收录原推发布于 2026.10.01

spicylemonade @spicey_lemonade原推发布于 2026.10.01
Gemini 4 Argon is a beast, ranking 4th on our RSI index. Furthermore, it generalizes extremely well; on evals like KSP Bench, it avoids plateauing. Along with Fable 5.1, GPT-6 Astra, and Opus 5.5, it belongs to a small group of models capable of beating the game with enough time.
这条是引用着另一条写的:x.com/officiallogank/status/2105388054274080946
x.com/spicey_lemonade/status/2105390555236839459采集于 2026.10.01 10:01