Use-case guides

Start with the work. Then choose the model.

Model rankings become useful only after you define the task, the failure cost, and the constraint that cannot move.

01Coding & agents

Build and maintain software

Choose models for planning, editing, review, tool use, and long-context repository work.

Coding · Tool use · ContextOpen guide →
02Reasoning

Solve constrained, high-stakes work

Compare reasoning depth, consistency, speed, and the cost of more deliberate inference.

Reasoning · Reliability · LatencyOpen guide →
03Cost optimization

Operate at production volume

Set a quality floor, model your token mix, and route work without paying frontier prices for every request.

Price · Volume · RoutingOpen guide →
04Private deployment

Run models on your own terms

Evaluate open weights, local hardware, privacy boundaries, and self-hosting overhead.

Privacy · Hardware · ControlOpen guide →
A practical sequence

Three questions before the leaderboard.

  1. 01

    What must the model do reliably? Define a quality floor using your own representative tasks.

  2. 02

    What cannot change? Name the budget, latency, privacy, context, or provider constraint.

  3. 03

    What evidence would change the choice? Compare the relevant metric and verify it against current sources.