The right AI for the job. Measured, not guessed.

Independent, hands-on evaluation: benchmarks, live pricing, and self-hosting tradeoffs weighed in practice, so you know when the frontier model earns its cost, when a lighter system is enough, and when not to use AI at all.
Subscribe to our newsletter
Price / 1M tokensbest available pricing
Claude Fable 5$10/$50PremiumClaude Opus 4.6$5/$25Claude Opus 5$5/$25Claude Sonnet 4.6$3/$15Gemini 3.1 Pro$2/$12Grok 4.20$1/$3Claude Haiku 4.5$1/$5Gemini 3.7 Flash$0.75/$4Gemini 3.0 Flash$0.50/$3GPT-5.1$0.25/$2v3.1$0.25/$0.95Qwen 3 30B A3B$0.05/$0.19V4$0.04/$0.08Best valueClaude Fable 5$10/$50PremiumClaude Opus 4.6$5/$25Claude Opus 5$5/$25Claude Sonnet 4.6$3/$15Gemini 3.1 Pro$2/$12Grok 4.20$1/$3Claude Haiku 4.5$1/$5Gemini 3.7 Flash$0.75/$4Gemini 3.0 Flash$0.50/$3GPT-5.1$0.25/$2v3.1$0.25/$0.95Qwen 3 30B A3B$0.05/$0.19V4$0.04/$0.08Best value

Live data

Cost vs. quality across 15 benchmarks

Pick a benchmark below. Models on the dashed line are Pareto-optimal: no other model offers better performance for less money.

Browse all modelsCompare API pricingView benchmark atlas

The promise

Spend where it changes the outcome. Not on the smallest model by default, not on the biggest.

Original Work

Tested first-hand, not just aggregated.

All evaluations
NEWMAR 26, 2026Analysis

We Benchmarked 7 OCR Models So You Don't Have To

Results from our own olmOCR-bench runs across OCR-specific models, general-purpose VLMs, and Tesseract. The main lesson: evaluation methodology changes scores more than most leaderboard readers realize.

14 min read
JAN 18, 2026Commentary

Claude Code is the New Cursor (and the Cycle Never Ends)

Everyone's screaming about Claude Code. A year ago, they screamed about Cursor. Before that, Copilot. The pattern is more interesting than the product, and reveals something uncomfortable about how we adopt tools.

12 min read
JAN 17, 2026Guide

When to Build Your Own AI Agent (and When Claude Code Is Enough)

When should you build your own AI agent instead of using Claude Code? A practical guide to the Anthropic Agent SDK, with mental models for understanding when and why to go beyond interactive AI.

17 min read

Head-to-head

Compare models side by side

Pick any models you're evaluating and compare benchmarks, pricing, and specs in one view.

SpecAnthropicClaude Opus 4.6 (Thinking)MetaSpark 1.2
AnthropicClaude Opus 5 (Thinking)
Arena ELO1,5051,5001,493
Input price$5.00/1M—$5.00/1M
Context1.0M—1.0M
Compare these modelsBuild your own comparison

Explore

Built for comparison, not browsing noise.

Core
135

Language Models

LLMs

Benchmarks, pricing, and tradeoffs that actually change a model decision.

Explore
Emerging
24

Extraction Systems

Document AI

Document parsing, OCR, and extraction systems evaluated as workflow components, not hype objects.

Explore
Open Models

Image AI

Which open image model and workflow to actually start with, answer-first.

Explore
Cost Index

Video AI

What AI video actually costs across APIs, wrappers, and credit plans.

Explore

Signal

AI News

Read all

Australia to require opt-out for social media algorithms, Albanese confirms

Xpeng announces automated production line using robots to mass-produce robots

Final version of Krea2 Turbo Distill 4 step LoRA released

New Twitter rebrands to Tweet.app following court ruling