| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Kimi K3: Open Frontier Intelligence | ✓ Link | 84.2 | Kimi K3 Max | 2026-07-27 |
| Hy4 preview | ✓ Link | 83.7 | Hy4 preview | 2026-08-28 |
| Hy3 | ✓ Link | 79.1 | Hy3 | 2026-07-02 |
| GLM-5.2: Built for Long-Horizon Tasks | ✓ Link | 76.8 | GLM-5.2 | 2026-06-16 |
| Muse Glimmer 30B: An On-Device Agentic Model | ✓ Link | 75.5 | Muse Glimmer-30B (High Reasoning) | 2026-10-17 |
| MiniMax M3: Frontier Coding, 1M Context, Native Multimodality — All in One Model | ✓ Link | 74.2 | MiniMax M3 | 2026-05-31 |
| GLM-5.1: Towards Long-Horizon Tasks | ✓ Link | 71.8 | GLM-5.1 | 2026-04-03 |
| Gemini 3.1 Pro: A smarter model for your most complex tasks | 69.2 | Gemini 3.1 Pro | 2026-02-19 | |
| GLM-5: From Vibe Coding to Agentic Engineering | ✓ Link | 67.8 | GLM-5 | 2026-02-11 |