Prompt Repetition Improves Non-Reasoning LLMs
About
When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.
Yaniv Leviathan, Matan Kalman, Yossi Matias• 2025
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| General Knowledge | MMLU (test) | Accuracy60.3 | 71 | |
| Science Question Answering | ARC Challenge (test) | Accuracy82.8 | 60 | |
| Question Answering | SciQ (test) | Accuracy92.9 | 36 | |
| Long-context evaluation | RULER 4k | -- | 35 | |
| Knowledge | OpenBookQA (test) | Accuracy78 | 19 | |
| Complex Reasoning | GSM8K (test) | Accuracy87.3 | 8 | |
| General knowledge and scientific retrieval | MedQA (test) | Accuracy51 | 8 | |
| Complex Reasoning | MMLU Pro (test) | Accuracy27.3 | 8 | |
| Long-context evaluation | RULER 8K context length | Accuracy82.3 | 4 | |
| Long-context evaluation | RULER 16k context length | Accuracy72.3 | 4 |
Showing 10 of 10 rows