gemini-4THREAD
Gemini 4 Argon 在 FrontierSWE 拿到 55.0%
Gemini 4 Argon 的 FrontierSWE 成绩为 55.0%，接近 Fable 5.1，仅落后 Opus 5.5 与 GPT-6 Astra。
Proximal
@ProximalHQ28 天前收录原推发布于 2026.10.01
THREAD
Gemini 4 Argon scores 55.0% on FrontierSWE The model is close to Fable 5.1 and only outperformed by Opus 5.5 and GPT-6 Astra
这条是引用着另一条写的：x.com/googledeepmind/status/2105388084154056939
Argon outperforms Gemini 3.8 Flash by a huge margin. It saturated Lean Proof Checker and Lua Native Compiler, tasks that Gemini 3.8 barely made progress on. Overall, it improved over 3.8 in 32 out of 34 tasks, only achieving lower scores in Weather Forecast and TORCS Racing Bot
Proximal @ProximalHQ原推发布于 2026.10.01
x.com/proximalhq/status/2105400332599865827采集于 2026.10.01 10:00