Simi Studio
Posts
Tags
Categories
English
简体中文
Simi Studio
Cancel
Posts
Tags
Categories
English
简体中文
Gemini
2026
Have Multimodal LLMs Matured: Early 2026 Real Testing
03-10
Computer Use Agent Roundup: Claude, GPT-4o, Gemini - Who Controls Computers Best
03-01
Gemini 3.1 Pro: 77.1% on ARC-AGI-2, Hallucination Rate Dropped from 88% to 44%
02-20
Gemini 3 Deep Think: 84.6% on ARC-AGI-2, 0.4% Shy of the AGI Signal Threshold
02-13
Gemini 2.0 Flash Thinking: How Does Google's Coding Stack Up
02-05
Gemini Reasoner: First Model to Surpass Human Average on Complex Reasoning
01-05
2025
LLM Selection Guide: Claude vs GPT-4o vs Gemini—Which One to Pick
12-27
2023
LLM Context Window Race: A Marathon With No Finish Line
10-15