Aider Polyglot: leaderboard
Aider polyglot coding-agent leaderboard over 225 Exercism tasks across C++, Go, Java, JavaScript, Python, and Rust.
Metric: Pass rate (%). Source: aider.chat. Status: saturated. 69 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (High) | 88 |
| 2 | GPT-5 (Medium) | 86.7 |
| 3 | O3 Pro (High) | 84.9 |
| 4 | GPT-5 (Low) | 81.3 |
| 5 | O3 (High) | 81.3 |
| 6 | Grok 4 (High) | 79.6 |
| 7 | O3 | 76.9 |
| 8 | Gemini 2.5 Pro (Preview 05-06) | 76.9 |
| 9 | DeepSeek V3.2 Exp | 74.2 |
| 10 | Gemini 2.5 Pro (Preview 03-25) | 72.9 |
| 11 | O4 Mini (High) | 72 |
| 12 | DeepSeek R1 0528 | 71.4 |
| 13 | Claude Opus 4 (20250514) | 70.7 |
| 14 | O1 (2024-12-17) (High) | 61.7 |
| 15 | O3 Mini (High) | 60.4 |
Interactive version: theaggregate.ai/benchmark?slug=aider-polyglot · How It Works · Data refreshed daily, snapshot 2026-09-05.