Comparison
Open Weights vs the Frontier: The Gap Is 3 Points and $8 a Million
Kimi K3 scores 60 on the Artificial Analysis Intelligence Index. Claude Opus 5 scores 63. That's the whole gap now — and the open model costs a third as much.
Topic hub
Benchmarks
Every Run the Eval review, comparison, and guide about Benchmarks — no hype, just receipts.
Explainer
GPT 5.6 Sol, Terra, and Luna: The New Tiers Explained
OpenAI is ditching the 'one big brain' approach for a tiered model family that looks more like a product lineup than a research project.