| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 72.9 | Qwen3.5-397B-A17B | 2026-02-16 |
| Ling-2.6-1T: A Trillion-Parameter Comprehensive Flagship Model for Complex Tasks | | 70.64 | Ling-2.6-1T | 2026-04-29 |
| WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents | | 67.63 | WEFT-14B | 2026-09-29 |
| NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness | ✓ Link | 67.43 | NeoHorse-1-9B | 2026-09-08 |
| Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale | ✓ Link | 66.81 | Ling-2.6-flash | 2026-06-13 |
| MiniCPM5-2B | ✓ Link | 66.6 | MiniCPM5-2B | 2026-09-07 |
| ERNIE 5.0 Technical Report | | 66.47 | ERNIE 5.0 | 2026-02-04 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 66.1 | Qwen3.5-9B | 2026-02-16 |
| Kwai Keye-VL-2.0 Technical Report | ✓ Link | 65.7 | Keye-VL-2.0-30B-A3B | 2026-06-09 |
| Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work | ✓ Link | 65.4 | Occamy-1.0 | 2026-09-04 |
| LFM2.5-24B-A2B: Built for Fast On-Device Agents | | 65.01 | LFM2.5-24B-A2B | 2026-10-13 |
| Qwen3.5-Omni Technical Report | | 63.3 | Qwen3.5-Omni-Plus | 2026-04-21 |
| Granite 4.2 LLMs: How They're Built | ✓ Link | 61.39 | Granite-4.2-30B | 2026-08-25 |
| CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents | | 58.0 | CLI-Universe-32B | 2026-06-22 |
| LFM2.5-2.6B: Deploy Agents Everywhere | ✓ Link | 56.88 | LFM2.5-2.6B | 2026-08-04 |
| Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts | ✓ Link | 56.50 | Nanbeige4.1-3B | 2026-02-13 |
| Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence | | 55.8 | Agent-World (14B) | 2026-04-20 |
| Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models | ✓ Link | 53.8 | Nanbeige4-3B-Thinking-2511 | 2025-12-06 |
| Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning | ✓ Link | 53.8 | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 2025-12-23 |
| Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation | | 52.9 | Nemotron-Cascade-2-30B-A3B | 2026-03-19 |
| LFM2.5-8B-A1B: an Even Better on-Device Mixture-of-Experts | ✓ Link | 49.73 | LFM2.5-8B-A1B | 2026-05-28 |
| ZAYA1-8B Technical Report | ✓ Link | 39.22 | ZAYA1-8B | 2026-05-06 |
| MiniCPM5-1B | ✓ Link | 25.15 | MiniCPM5-1B (Thinking) | 2026-05-25 |
| LFM2.5-350M: No Size Left Behind | | 21.86 | LFM2.5-350M | 2026-03-31 |
| LFM2.5-VL-450M: Structured Visual Intelligence, Edge to Cloud | | 21.08 | LFM2.5-VL-450M | 2026-04-08 |
| LFM2.5-230M: Built to Run Anywhere | | 21.03 | LFM2.5-230M | 2026-06-25 |