ended6월 9일· 1 sources
I Tested Claude Opus 4, GPT-4.1, GPT-4o, Sonnet 4, and Gemini 2.5 Pro on 10 Adversarial Scenarios. They All Broke on the Same One.
Why it matters
TL;DR Last week I benchmarked 5 open-weight models (Llama 4 Scout, Llama 3.3 70B, Qwen3 32B, GPT-OSS, Gemini 2.5 Flash) and the best scored 62.5%. People asked the obvious follow-up: does the closed-f...
1
Sources
+0
24h
—
Growth
4d
Active