| Paper | Code | Pass@1 | ModelName | ReleaseDate |
|---|---|---|---|---|
| GPT-5.6: Frontier intelligence that scales with your ambition | ✓ Link | 0.58 | GPT-5.6 Sol | 2026-07-09 |
| Introducing GPT-5.5 | 0.556 | GPT-5.5 | 2026-04-23 | |
| Introducing GPT-5.4 | 0.546 | GPT-5.4 | 2026-03-05 | |
| DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence | ✓ Link | 0.518 | DeepSeek-V4-Pro Max | 2026-04-26 |
| Seed2.1 Model Card: Agentic Intelligence for Productivity | 0.506 | Seed2.1 Pro | 2026-06-23 | |
| Step 3.7 Flash | ✓ Link | 0.4951 | Step 3.7 Flash | 2026-05-29 |
| Gemini 3.1 Pro: A smarter model for your most complex tasks | 0.488 | Gemini 3.1 Pro | 2026-02-19 | |
| Hy3 | ✓ Link | 0.485 | Hy3 | 2026-07-02 |
| GLM-5.2: Built for Long-Horizon Tasks | ✓ Link | 0.482 | GLM-5.2 | 2026-06-16 |
| Introducing GPT-5.2 | 0.463 | GPT-5.2 | 2025-12-11 | |
| The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence | ✓ Link | 0.463 | MiniMax-M2.7 | 2026-05-26 |
| GLM-5.1: Towards Long-Horizon Tasks | ✓ Link | 0.407 | GLM-5.1 | 2026-04-03 |
| DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use | ✓ Link | 0.083 | Dive-8B (RL) | 2026-03-10 |