benchmarks / aider-polyglot
Aider Polyglot
percent correct. Status active. Contamination risk med. Maintainer Aider / Epoch collection. Source.
| Model | Score | Date | Kind |
|---|---|---|---|
| GPT Oss 120B | 41.8 | 2025-08-05 | observation |
| Qwen3 235B A22b | 59.6 | 2025-04-29 | observation |
| DeepSeek V3.2 Exp | 70.2 | 2025-09-29 | observation |
| DeepSeek V3.2 Exp Thinking | 74.2 | 2025-09-29 | observation |
| GPT-5 | 81.3 | 2025-08-25 | observation |
| GPT-5 | 86.7 | 2025-08-25 | observation |
| GPT-5 | 88 | 2025-08-23 | observation |
| O3 | 76.9 | 2025-04-16 | observation |
| Grok 3 Mini Beta | 34.7 | 2025-04-10 | observation |
| Openhands LM 32B V0.1 | 10.2 | 2025-04-19 | observation |
| Kimi K2 Instruct | 59.1 | 2025-07-12 | observation |
| Grok 4 0709 | 79.6 | 2025-07-09 | observation |
| O3 Pro | 84.9 | 2025-06-28 | observation |
| Gemini 2.5 Pro Preview 05.06 | 76.9 | 2025-05-07 | observation |
| Gemini 2.5 Pro Preview 06.05 | 79.1 | 2025-06-06 | observation |
| Gemini 2.5 Flash Preview 05.20 | 44 | 2025-05-26 | observation |
| Claude Sonnet 4 | 56.4 | 2025-05-24 | observation |
| Claude Sonnet 4 20250514 | 61.3 | 2025-05-24 | observation |
| Claude Opus 4 | 70.7 | 2025-05-25 | observation |
| Claude Opus 4 20250514 | 72 | 2025-05-25 | observation |
| Qwen3 32B | 40 | 2025-05-08 | observation |
| Llama 4 Maverick 17B 128e Instruct | 15.6 | 2025-04-06 | observation |
| GPT-4.1 Mini | 32.4 | 2025-04-14 | observation |
| GPT-4.1 Nano | 8.9 | 2025-04-14 | observation |
| ChatGPT 4O 03.27 2025 | 45.3 | 2025-03-29 | observation |
| Gemini 2.5 Flash Preview 04.17 | 47.1 | 2025-04-20 | observation |
| Grok 3 Mini Beta | 49.3 | 2025-04-10 | observation |
| GPT-4.1 | 52.4 | 2025-04-14 | observation |
| Grok 3 Beta | 53.3 | 2025-04-10 | observation |
| DeepSeek V3 0324 | 55.1 | 2025-03-24 | observation |