| Paper | Code | F1 | ModelName | ReleaseDate |
|---|---|---|---|---|
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | ✓ Link | 92.2 | DeepSeek-R1 (3-shot) | 2025-01-22 |
| DeepSeek-V3 Technical Report | ✓ Link | 91.6 | DeepSeek-V3 | 2024-12-27 |
| Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models | ✓ Link | 86.7 | Youtu-LLM 2B (3-shot) | 2025-12-31 |
| Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation | ✓ Link | 75.7 | T5Gemma 9B-9B PrefixLM | 2025-04-08 |
| Gemma 2: Improving Open Language Models at a Practical Size | ✓ Link | 74.2 | Gemma 2 27B (3-shot) | 2024-07-31 |