Aider Polyglot
Aider · polyglot-225-5dc9490bb35f · A 225-exercise coding benchmark across six programming languages, published with per-run configuration and pass counts by Aider.
Model ranking
Publisher benchmark →Source | |||||||
|---|---|---|---|---|---|---|---|
| #1 | Kimi-K2-InstructMoonshot AI | 59.11 | 1,617.1 | 225 | diff; aider 0.85.3.devtotal | Recomputedwinner eligible | Third-party benchmark |
| #2 | gpt-oss-120bOpenAI | 41.78 | 3,806.6 | 225 | diff; aider 0.85.3.devtotal | Recomputedwinner eligible | Third-party benchmark |
| #3 | Llama-4-Maverick-17B-128E-InstructMeta | 15.56 | — | 225 | whole; aider 0.81.2.devunknown | Recomputedwinner eligible | Third-party benchmark |
3 models ranked by the best winner-eligible current-version score when available, otherwise the best publisher-artifact score; highest first. Observed Aug 29, 2026.
Ranking protocol
pass rate 2 · percent. Each model appears once; verified winner-eligible runs take precedence, and missing models are not imputed.
Acquisition coverage
3 published models from 69 source rows; 65 source identities remain quarantined.
Primary evidence