Aider
by Aider (open-source project)
AI pair programming in your terminal
Overview
Publisher-provided · source: github.com · compiled 15 Oct 2026
Edits code in your local git repository through a chat interface, commits changes automatically and works with many model providers.
Capabilities
- code editing
- multi file changes
- terminal commands
- codebase search
- auto commit
Benchmark results
Measured task performance on a published benchmark suite. Each metric is shown separately.
Not yet evaluated on a full benchmark suite.
It has independent results on the Coding Core (pilot) (5 tasks, latest 17 Oct 2026), listed under Benchmark history. A pilot has too few tasks to be representative, so it isn't ranked and gives no headline score or levels.
Benchmark history
Every run, tied to the exact agent version, model and configuration.
| Date | Version | Suite | Model | Source | Success | Cost / success | Median time |
|---|---|---|---|---|---|---|---|
| 17 Oct 2026 | 0.86.2 | Coding Core (pilot) v1.0-pilotPilot, not ranked | claude-opus-5-5 | Independently evaluatedMeasured by this platform's evaluation harness under documented, reproducible conditions. | 100.0 | $0.165 | 55s |
- 17 Oct 2026, Coding Core (pilot): Held for review (cc-06 #1: assigns to test framework objects; cc-06 #3: assigns to test framework objects). Released by Agent Ledger operator after review: Both flags (cc-06 #1, #3) were arrow functions in agent-written tests, not assignments to the test framework; diffs read in full, false positive. Rule fixed in grader 1.1.1.
Publisher claims
What the developer says about performance. Kept separate from measured results and not verified by us.
No performance claims recorded.
Community reports
Experiences reported by users. Not verified.
No community reports yet.
Known limitations
None documented yet. Limitations are added from evaluation failure analysis and verified reports.