gemini-4IMAGE
Gemini 4 Argon 多项 benchmark 超 GPT-6 Astra
爆料称 Gemini 4 Argon 在 DeepSWE、Vibe Code Bench、LABBench 2、GraphWalks、LVBench、Vals Finance Agent v2 上多数领先 GPT-6 Astra、Claude Fable 5.1 与 Opus 5.5。
O🌷
@Octoberry20 天前收录原推发布于 2026.10.14
O🌷 @Octoberry原推发布于 2026.10.14
Gemini 4 argon beats gpt-6 astra, claude fable 5.1 and opus 5.5 on most of these benchmarks 77.9% on DeepSWE v1.1 91.9% on Vibe Code Bench 88.8% on LABBench 2 99.7% on GraphWalks (up to 128k) 91.7% on LVBench 65.4% on Vals Finance Agent v2
这条是引用着另一条写的：x.com/0xtoberry/status/2110040189452050833
x.com/octoberry/status/2110073443274444927采集于 2026.10.14 10:02