| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Introducing GPT-5 | 88 | GPT-5 (High) | 2025-08-07 | |
| Introducing OpenAI o3 and o4-mini | ✓ Link | 81.3 | OpenAI o3 (High) | 2025-04-16 |
| Qwen3-Coder-Next Technical Report | ✓ Link | 66.2 | Qwen3-Coder-Next | 2026-02-28 |
| Introducing OpenAI o1 | 64.4 | OpenAI o1 (High) | 2024-09-12 | |
| Kimi K2: Open Agentic Intelligence | ✓ Link | 60.0 | Kimi K2 | 2025-07-28 |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | ✓ Link | 53.3 | DeepSeek-R1 | 2025-01-22 |
| Qwen3-Next | 49.8 | Qwen3-Next-80B-A3B-Instruct | 2025-09-09 | |
| DeepSeek-V3 Technical Report | ✓ Link | 49.6 | DeepSeek-V3 | 2024-12-27 |
| gpt-oss-120b & gpt-oss-20b Model Card | 44.4 | gpt-oss-120b (High) | 2025-08-08 | |
| OpenThoughts-Agent: Data Recipes for Agentic Models | ✓ Link | 32.4 | OpenThinkerAgent-32B | 2026-06-23 |