LATEST_
All posts in reverse chronological order
[793] September 2026
Benchmarks
Z-Image Turbo vs Qwen-Image 2.1: my RTX 4090 test
Benchmarks
Lesser-Known AI Image Generators Beat Midjourney: 6 Models Tested
Benchmarks
GPT-6 Luna: OpenAI’s Cheapest Model Passed My Tests for $0.0024
Benchmarks
What Do Chatbots Know About the AI Act? 8 of 9 Models Failed
Benchmarks
LLMs Can’t Reason About Code Execution - SWE-Flux Benchmark
Benchmarks
Midjourney vs Gemini: Image Generator Test 2026
Benchmarks
7 Local AI Models on RTX 4090 vs Cloud: Non-English Writing Test
Benchmarks
Claude Opus 5.5 in Claude Code: 3-Hour AI Agent Test Run
Benchmarks
Claude Opus 5.5 Motion Graphics: 60s Showreel from One Prompt
Benchmarks
Wan 2.2 on RTX 4090: timings, VRAM and four test clips
Benchmarks
Mushroom Identification Apps: AI Test on 6 Photos
Benchmarks
Best AI Video Generators 2026: 10 Models Ranked with Audio
Benchmarks
Claude Sonnet 5.5 vs GPT-5.6 Sol Pro: Which Model to Choose
Benchmarks
Claude Sonnet 5.5 Price: Cost per Million Tokens in 2026
Benchmarks
GPT-6 Sol vs Claude Sonnet 5: Price and Context Compared
Benchmarks
GPT-6 Sol Price: Cost Per Million Tokens and Monthly Budget
Benchmarks
Choosing Between Grok 4.7, Claude, GPT-6, and Kimi K3
Benchmarks
What 500,000 Tokens Means for Grok 4.7 in Practice
Benchmarks
Who Should Use Grok 4.7 Based on Price and Context
Benchmarks
Grok 4.7 vs Kimi K3: Price and Context Comparison
Benchmarks
Grok 4.7 Pricing: Real Costs for Typical Workloads
Benchmarks
GPT-6 Astra alternatives: six models from 2x to 26x cheaper on output
Benchmarks
Qwen 3.8 vs GPT-5.6 Luna: 7x Price Gap, Same Context
Benchmarks