| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | ✓ Link | 82.5 | DeepSeek-R1 | 2025-01-22 |
| Hunyuan Dense V1 | ✓ Link | 78.6 | Hunyuan-7B-Instruct | 2025-07-30 |
| Kimi K2: Open Agentic Intelligence | ✓ Link | 77.1 | Kimi K2 | 2025-07-28 |
| QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management | ✓ Link | 74.76 | QwenLong-L1.5-30B-A3B | 2025-12-15 |
| GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment | ✓ Link | 74.5 | GoLongRL-30B-A3B (w. GRPO) | 2026-05-19 |
| DeepSeek-V3 Technical Report | ✓ Link | 73.3 | DeepSeek-V3 | 2024-12-27 |