| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition | ✓ Link | 48.3 | Sage-A1.5 | 2026-10-20 |
| Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent | ✓ Link | 40.0 | Agents-A1 | 2026-06-29 |
| Introducing GPT-5.4 | 36.7 | GPT-5.4 Pro | 2026-03-05 | |
| Rufus-Air: An Open LLM Post-Training Recipe | 35.1 | Rufus-Air | 2026-09-24 | |
| Seed2.1 Model Card: Agentic Intelligence for Productivity | 33.3 | Seed2.1 Turbo | 2026-06-23 | |
| Hy3 | ✓ Link | 21.3 | Hy3 | 2026-07-02 |
| Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling | ✓ Link | 11.7 | SU-01 | 2026-05-13 |
| SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning | ✓ Link | 5.0 | Intern-S2-OPD | 2026-08-14 |