| Gemini 3.1 Pro: A smarter model for your most complex tasks | | 99.3 | Gemini 3.1 Pro | 2026-02-19 |
| Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning | | 99.1 | EDV (Ours) | 2026-06-23 |
| Introducing GPT-5.4 | | 98.9 | GPT-5.4 | 2026-03-05 |
| Introducing GPT-5.2 | | 98.7 | GPT-5.2 | 2025-12-11 |
| Introducing GPT-5.5 | | 98.0 | GPT-5.5 | 2026-04-23 |
| MiniCPM5-2B | ✓ Link | 97.1 | MiniCPM5-2B | 2026-09-07 |
| Kolibri: A Sovereign European Model on the Pareto Frontier | ✓ Link | 94.7 | Kolibri | 2026-10-03 |
| KAT-Coder-V2 Technical Report | | 93.9 | KAT-Coder-V2 | 2026-03-29 |
| Rufus-Air: An Open LLM Post-Training Recipe | | 93.0 | Rufus-Air | 2026-09-24 |
| Unlocking Lossless Speedups in LLMs via Discrete Diffusion | ✓ Link | 90.1 | Uno (K2-Horizon-7B-Uno) | 2026-09-03 |
| LFM2.5-8B-A1B: an Even Better on-Device Mixture-of-Experts | ✓ Link | 88.07 | LFM2.5-8B-A1B | 2026-05-28 |
| PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents | ✓ Link | 86.6 | PolicyGuide (GPT-5.4) | 2026-08-20 |
| Command A+ | | 85 | Command A+ | 2026-05-20 |
| LongCat-Flash Technical Report | ✓ Link | 73.68 | LongCat-Flash | 2025-09-01 |
| K-EXAONE Technical Report | ✓ Link | 73.5 | K-EXAONE (236B, reasoning) | 2026-01-05 |
| EXAONE 4.5 Technical Report | ✓ Link | 73.0 | EXAONE 4.5 (Reasoning) | 2026-04-09 |
| SkillX: Automatically Constructing Skill Knowledge Bases for Agents | ✓ Link | 71.88 | SkillX (GLM-4.6) | 2026-04-06 |
| Kimi K2: Open Agentic Intelligence | ✓ Link | 65.8 | Kimi K2 | 2025-07-28 |
| Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem | ✓ Link | 30.92 | ROME (30B MoE, activated 3B) | 2025-12-31 |
| ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training | | 30.9 | Qwen3-SE-32B | 2026-02-06 |
| ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction | | 30.03 | GRPO+ARC (Qwen3-4B) | 2026-08-13 |
| LFM2.5-350M: No Size Left Behind | | 18.86 | LFM2.5-350M | 2026-03-31 |
| LFM2.5-230M: Built to Run Anywhere | | 5.26 | LFM2.5-230M | 2026-06-25 |