Weights use min–max normalization within this comparison (higher or lower as labelled), then a weighted mean on a 0–100 scale. Equal values receive 50. Criteria with no measurements are excluded. A thing missing any selected, measured criterion is unranked; missing is never zero. All-zero weights give no ranking. Scores express these preferences, not statistical significance. Dates are source dates or explicitly labelled observation dates. No costs or benchmark results are estimated. Different benchmark versions are separate criteria. Builder and version history are reserved for a later release. Only the latest hundred public runs from each of codes.patch and codes.ticket are read; only verified runs are eligible. Benchmark version and model form separate criteria; newest verified run per harness and cohort is shown, with the harness version in its source label. Harness configuration prices are not product prices and are not used.

AI coding agents

Aider

Claude Code

Claude Code (another provider)

Codex

Command Code

DeepSeek

MiniMax Code

Muse Code

OpenCode

OpenVibe.AI

Your own model

Method

Sources

Thing
Aider	Unranked	Not measured
Claude Code	Unranked	Not measured
Claude Code (another provider)	Unranked	Not measured
Codex	Unranked	Not measured
Command Code	Unranked	Not measured
DeepSeek	Unranked	Not measured
MiniMax Code	Unranked	Not measured
Muse Code	Unranked	Not measured
OpenCode	Unranked	Not measured
OpenVibe.AI	Unranked	Not measured
Your own model	Unranked	Not measured