Gemini 4 Argon Wins 12 of 18 Benchmarks. Code Isn't One.
Gemini 4 Argon Wins 12 of 18 Benchmarks. Code Isn't One. Google just dropped Gemini 4 Argon , and the numbers are hard to argue with. The model leads 12 of 18 published benchmarks against GPT-6 Astra and Claude Opus 5.5 -- scoring 77.9% on DeepSWE v1.1, 91.7% on LVBench video understanding, and landing the number one slot on LMArena Text Arena with 1,525 points. It ships a 1-million-token output…
Google unveiled Gemini 4 Argon, a new AI model that outperforms GPT-6 Astra, Astra, and Claude Opus 5.5 on 12 out of 18 benchmarks. Argon excels in reasoning, knowledge, and multimodal tasks, securing top spots in DeepSWE v1.1, LVBench video understanding, and LMArena Text Arena. However, it lags behind in code-related benchmarks, ranking 8th in Code Arena WebDev.
Notably, Argon offers a 1-million-token output window, surpassing previous models' 64K token cap. Despite its impressive performance, Argon's cost per task is higher than GPT-6 Astra and Claude Opus 5.5, though it delivers superior token consumption efficiency.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
