Best of
The best AI for the job
Picks backed by live benchmarks, live prices, and a stated methodology. Every one runs in your idapt workspace.
Best tools
Best models by job
The models that ship working code.Coding picks backed by live benchmark rankings and real prices, from frontier reviewers to fast pair-programmers.The models writers actually keep.Writing picks judged on voice-following, long-document stamina, and edit quality, with live per-token prices.Models that cite what survives.Research picks judged on knowledge benchmarks, context for source sets, and citation discipline with live web search.Models that show their work.Reasoning picks from the math and logic lanes: AIME, MATH-500, and HLE among the named benchmarks, with live prices.Frontier answers at commodity prices.The models that deliver the most per dollar, with live per-million-token prices from the catalog.Open weights at the frontier.The open-weight models that stand next to closed flagships on the live rankings, hosted or on your own hardware.Serious models, your hardware.The local models worth running via Ollama, by hardware tier, with a cloud fallback when the job outgrows the machine.Real local AI on 8 GB.Every pick's quantization recommends at most 8 GB in the catalog's hardware data: what fits, what it trades, how to run it.The models that cost nothing to run.The two free lanes, compared: catalog models covered by the free daily allowance, and local models running on your own machine.Models that hold the whole thing.Ranked by the context window in the live catalog, from million-token readers to a two-million-token outlier, priced per token.Models that read what you see.Models that accept images and return analysis: screenshots, charts, scans, and photos, verified against live capability data.The models that get the number right.Math picks straight from the live math lane (AIME and MATH-500 among the named benchmarks), with prices beside each pick.Translation that survives a back-check.Multilingual picks plus the workflow that catches drift: translate on one model, back-translate on another, keep what agrees.The image models that earn their prompts.Image picks compared on text rendering, editing, and photorealism, with side-by-side output comparison built in.Text to moving picture, compared.Video picks across realism, audio, and price per second, from quick drafts to flagship shots, in one workspace.Voices you can ship.TTS picks across realism, languages, and price, with dozens of voices searchable by style in one catalog.Narration that lasts a whole book.TTS picks judged on hours-long stability, with live per-1,000-character rates you can multiply out to book scale.