| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 94.9 | Qwen3.5-397B-A17B | 2026-02-16 |
| Qwen3.5-Omni Technical Report | | 94.2 | Qwen3.5-Omni-Plus | 2026-04-21 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 94.0 | Qwen3.5-122B-A10B | 2026-02-16 |
| Introducing efficiency focused "Thinking CAP" model series | ✓ Link | 93.9 | ThinkingCap-Qwen3.6-27B | 2026-07-06 |
| Qwen3-VL Technical Report | ✓ Link | 93.7 | Qwen3-VL-235B-A22B-Thinking | 2025-11-26 |
| Qwen3.6 | ✓ Link | 93.5 | Qwen3.6-27B | 2026-04-21 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 93.3 | Qwen3.5-35B-A3B | 2026-02-16 |
| Qwen3.6 | ✓ Link | 93.3 | Qwen3.6-35B-A3B | 2026-04-21 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 93.2 | Qwen3.5-27B | 2026-02-16 |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | ✓ Link | 92.9 | DeepSeek-R1 | 2025-01-22 |
| Qwen3 Technical Report | ✓ Link | 92.7 | Qwen3-235B-A22B (Thinking) | 2025-05-14 |
| Kimi K2: Open Agentic Intelligence | ✓ Link | 92.7 | Kimi K2 | 2025-07-28 |
| EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes | ✓ Link | 92.3 | EXAONE 4.0 32B (Reasoning) | 2025-07-15 |
| Qwen3-Coder-Next Technical Report | ✓ Link | 91.18 | Qwen3-Coder-Next | 2026-02-28 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 91.1 | Qwen3.5-9B | 2026-02-16 |
| Qwen3-Next | | 90.9 | Qwen3-Next-80B-A3B-Instruct | 2025-09-09 |
| On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability | ✓ Link | 90.68 | Qwen3.8-Flash-Next-Base | 2026-08-31 |
| Qwen3-Omni Technical Report | ✓ Link | 89.7 | Qwen3-Omni-Flash-Thinking | 2025-09-22 |
| SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture | ✓ Link | 89.44 | SenseNova-U1-A3B-MoT | 2026-05-12 |
| Qwen3 Technical Report | ✓ Link | 89.2 | Qwen3-235B-A22B (Non-thinking) | 2025-05-14 |
| DeepSeek-V3 Technical Report | ✓ Link | 89.1 | DeepSeek-V3 | 2024-12-27 |
| Announcing Bonsai 27B: The First 27B-Class Model to Run on a Phone | ✓ Link | 88.05 | Ternary Bonsai 27B | 2026-07-14 |
| Qwen2.5 Technical Report | ✓ Link | 86.8 | Qwen2.5-72B-Instruct | 2024-12-19 |
| Unified Audio Intelligence Without Regressing on Text Intelligence | | 86.4 | Audex 30B-A3B | 2026-07-06 |
| SenseNova-U1.5: Towards Native Unified Visual Intelligence | ✓ Link | 86.33 | SenseNova-U1.5 8B-Think | 2026-09-10 |
| Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation | | 86.3 | Nemotron-Cascade-2-30B-A3B | 2026-03-19 |
| Mellum2 Technical Report | ✓ Link | 86.2 | Mellum 2 Thinking | 2026-05-29 |
| Qwen2.5-VL Technical Report | ✓ Link | 85.9 | Qwen2.5-VL-72B | 2025-02-19 |
| dots.llm1 Technical Report | ✓ Link | 85.1 | dots.llm1.inst | 2025-06-06 |
| Data Science and Technology Towards AGI Part I: Tiered Data Management | ✓ Link | 84.7 | MiniCPM5-2B | 2026-02-09 |
| MiniCPM5-2B | ✓ Link | 84.7 | MiniCPM5-2B | 2026-09-07 |
| Loop the Loopies! | | 83.61 | Loopie-20B-A2B (Thinking) | 2026-07-17 |
| Ministral 3 | | 82.0 | Ministral 3 (14B) | 2026-01-13 |
| Raon-Speech Technical Report | ✓ Link | 78.87 | Raon-Speech | 2026-04-08 |
| See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents | | 78.57 | Dense alignment (cross-model KV-cache transformation) | 2026-06-11 |
| Draft-KV: Learning Useful Latent Communication Between Language Models | ✓ Link | 78.04 | Draft-KV (Qwen3-8B -> Qwen2.5-0.5B-Instruct) | 2026-09-28 |
| Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision | ✓ Link | 76.8 | Youtu-VL (4B) | 2026-01-27 |
| Improved Large Language Diffusion Models | ✓ Link | 76.4 | iLLaDA 8B Instruct | 2026-06-24 |
| Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models | ✓ Link | 75.8 | Youtu-LLM 2B | 2025-12-31 |
| Qwen2.5-Omni Technical Report | ✓ Link | 71.0 | Qwen2.5-Omni-7B | 2025-03-26 |
| MiniCPM5-1B | ✓ Link | 70.06 | MiniCPM5-1B (Thinking) | 2026-05-25 |