Model results

Aider Polyglot Benchmark

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

Aider Polyglot Benchmark

Source: Aider Polyglot Benchmark (reviewed publisher results)
Version: polyglot-225
Measurement date: 2025-06-27
Metric: % · Higher is better
Evaluation scope: 225 polyglot tasks; 224 attempted cases reported; two attempts; edit format architect; Aider commit 4f4f00f-dirty; configuration o3 (high) + gpt-4.1

Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

o3
openai/o3-2025-04-16
78.2%
View modelEvidence independent