| InCoder-32B-Thinking: Industrial Code World Model for Thinking | ✓ Link | 81.3 | InCoder-32B-Thinking | 2026-04-03 |
| NVIDIA Nemotron 3: Efficient and Open Intelligence | ✓ Link | 81.19 | Nemotron 3 Super | 2025-12-24 |
| Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities | | 74.2 | Gemini 2.5 Pro | 2025-07-07 |
| GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | ✓ Link | 72.9 | GLM-4.5 (355B) | 2025-08-08 |
| Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning | ✓ Link | 70.8 | Apriel-1.5-OpenReasoner | 2026-04-02 |
| Qwen3 Technical Report | ✓ Link | 70.7 | Qwen3-235B-A22B (Thinking) | 2025-05-14 |
| GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | ✓ Link | 70.7 | GLM-4.5-Air | 2025-08-08 |
| Embarrassingly Simple Self-Distillation Improves Code Generation | ✓ Link | 70.7 | GPT-OSS-20B (high) + SSD | 2026-04-01 |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | ✓ Link | 65.9 | DeepSeek-R1 | 2025-01-22 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 63.2 | Nemotron 3 Nano Omni | 2026-04-27 |
| How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data | ✓ Link | 62.87 | TESSY | 2026-03-23 |
| Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation | ✓ Link | 60.8 | Lightning OPD (Qwen3-30B-A3B) | 2026-04-14 |
| Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities | | 59.3 | Gemini 2.5 Flash | 2025-07-07 |
| Post-Trained MoE Can Skip Half Experts via Self-Distillation | ✓ Link | 58.2 | ZEDA (Qwen3-30B-A3B) | 2026-05-18 |
| InCoder-32B: Code Foundation Model for Industrial Scenarios | ✓ Link | 53.3 | InCoder-32B (32B) | 2026-03-17 |
| The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation | ✓ Link | 43.4 | Llama 4 Maverick | 2025-04-05 |
| Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models | ✓ Link | 40.9 | Nanbeige4-3B-Base + OpenThoughts3 SFT (extra data) | 2025-12-06 |
| Qwen3 Technical Report | ✓ Link | 35.3 | Qwen3-235B-A22B (Non-thinking) | 2025-05-14 |
| The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation | ✓ Link | 32.8 | Llama 4 Scout | 2025-04-05 |
| dots.llm1 Technical Report | ✓ Link | 32.0 | dots.llm1.inst | 2025-06-06 |
| NGM: A Plug-and-Play Training-Free Memory Module for LLMs | ✓ Link | 29.94 | Qwen3-14B + NGM | 2026-05-16 |