Why do LLM pelicans look like this?(arcfu.com)
127 points by pcwelder | 116 comments
Blog post examining why SVGs generated by various LLMs for the prompt "pelican riding a bicycle" all look strikingly similar, with a gallery comparing models.
#model-comparison on Hacker News
9 stories tagged model-comparison, newest first.
AI Model Groupthink(magicnumbers.io)
15 points by io84 | 3 comments
Blog post analyzing a tool that polls 12 AI models for top-three rankings, finding Chinese models more likely to agree with the wider consensus.
LLM Ass Bench(assbench.com)
108 points by fragmede | 32 comments
LLM AssBench is a website comparing interactive 3D models of a human buttocks in a thong, each generated by a different LLM from the same prompt.
Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard(artificialanalysis.ai)
358 points by aarondong | 211 comments
Artificial Analysis page comparing AI models on intelligence, output speed, latency, price and context window, showing Claude Opus 5 at the top for intelligence.
$100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol(tryai.dev)
362 points by hershyb_ | 480 comments
TryAI blog post comparing Claude Fable 5 and GPT-5.6 Sol as autonomous agents directing a music video on a $100 budget with web search and ffmpeg.
DeepSeek V4 Pro beats GPT-5.5 Pro on precision(runtimewire.com)
365 points by yogthos | 184 comments
A Runtimewire head-to-head article claiming DeepSeek V4 Pro outperforms GPT-5.5 Pro on precision tasks like instruction following and schema matching.
AI World Clocks(clocks.brianmoore.com)
1283 points by waxpancake | 361 comments
A web page showing analog clocks rendered every minute by nine different AI models, displaying their often distorted attempts side by side.
Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison(composio.dev)
392 points by mraniki | 275 comments
A Composio blog post comparing the coding abilities of Google's Gemini 2.5 Pro and Anthropic's Claude 3.7 Sonnet.
Show HN: Countless.dev – A website to compare every AI model: LLMs, TTSs, STTs(countless.dev)
328 points by ahmetd | 70 comments
Countless.dev is a free, open-source website for comparing AI models such as LLMs, TTS, and STT, with price comparison, a pricing calculator, and versus views.