| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | ✓ Link | 60.4 | GLM-4.5 (355B) | 2025-08-08 |
| Claude 3.7 Sonnet and Claude Code | 58.4 | Claude 3.7 Sonnet | 2025-02-24 | |
| Claude Opus 4.1 | 56.0 | Claude Opus 4.1 | 2025-08-05 | |
| Introducing OpenAI o3 and o4-mini | ✓ Link | 52.0 | OpenAI o3 | 2025-04-16 |
| Introducing OpenAI o1 | 50.0 | OpenAI o1 | 2024-09-12 | |
| gpt-oss-120b & gpt-oss-20b Model Card | 49.2 | gpt-oss-120b | 2025-08-08 | |
| ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction | 44.0 | GRPO + ARC (Qwen3-8B) | 2026-08-13 | |
| CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents | 27.5 | CAST Policy-4B + Critic-4B | 2026-08-31 |