Personal model radar

See what changed around the models you care about

Follow practical tasks, revisit saved models, and keep lightweight decision records without creating an account.

Saved on this device only
Latest comparable period
Reviewed through

Start here: save models and follow tasks. Future visits will show what changed since this snapshot.

1 up · 361 down · 11 new in this snapshot

01

Saved models

Latest public movement is shown only where an exact official version maps to the comparable source.

Browse model rankings

02

Follow real-work tasks

Choose the work you revisit most. This changes your radar, not the public ranking.

Open task ranking

Everyday work

Drafting, analysis, planning, and mixed office tasks.

Coding & debugging

Implementation, defect analysis, tests, and technical trade-offs.

Deep research

Multi-step analysis, evidence synthesis, and reasoned conclusions.

Documents & grounded Q&A

Long files, summaries, citations, and answers bounded by supplied text.

Customer support

Clear, safe, policy-aware replies to common requests.

Chinese & multilingual work

Chinese-first writing, translation, localization, and mixed-language tasks.

Image & multimodal work

Images, documents, extraction, and mixed visual-text reasoning.

Cost-efficient production

Reduce successful-task cost without choosing by price alone.

Private & local deployment

Open-weight candidates for controlled data paths and self-hosting.

Fast production workflows

High-volume classification, extraction, routing, and short responses.

03

Return summary

Show a weekly-style summary on this page when you return. OpenGPT does not send email or run in the background.

This preference stays in this browser.

04

Saved decision records

These records contain task and model IDs only—never prompts, answers, or API keys.

No decision record has been saved yet. Open a task ranking to create one.

Open task ranking