Mathematics on AIME 26
70AccuracyAutoGen
Evaluation Results
| Method | Links | |
|---|---|---|
| AutoGenBase Model=GPT-OSS:120B, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 70 | |
| Agent FrameworkBase Model=GPT-OSS:120B, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 63.33 | |
| LobsterBase Model=GPT-OSS:120B, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 60 | |
| LangGraphBase Model=GPT-OSS:120B, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 60 | |
| Agent Q-MixBase Model=GPT-OSS:120B2026.04 | 60 | |
| AutoGenBase Model=Gemini-3.1-Flash-Lite, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 60 | |
| Agent Q-MixBase Model=Gemini-3.1-Flash-Lite2026.04 | 60 | |
| Agent FrameworkBase Model=Gemini-3.1-Flash-Lite, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 56.67 | |
| GTDBase Model=Gemini-3.1-Flash-Lite, Framework Category=Adaptive topology methods2026.04 | 46.67 | |
| GPTSwarmBase Model=GPT-OSS:120B, Framework Category=Adaptive topology methods2026.04 | 43.33 | |
| G-DesignerBase Model=GPT-OSS:120B, Framework Category=Adaptive topology methods2026.04 | 43.33 | |
| TopoDIMBase Model=Gemini-3.1-Flash-Lite, Framework Category=Adaptive topology methods2026.04 | 43.33 | |
| GTDBase Model=GPT-OSS:120B, Framework Category=Adaptive topology methods2026.04 | 40 | |
| GPTSwarmBase Model=Gemini-3.1-Flash-Lite, Framework Category=Adaptive topology methods2026.04 | 40 | |
| MaASBase Model=Gemini-3.1-Flash-Lite, Framework Category=Adaptive topology methods2026.04 | 40 | |
| LLM-DebateBase Model=GPT-OSS:120B, Framework Category=Static multi-agent2026.04 | 36.67 | |
| G-DesignerBase Model=Gemini-3.1-Flash-Lite, Framework Category=Adaptive topology methods2026.04 | 36.67 | |
| LobsterBase Model=Gemini-3.1-Flash-Lite, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 36.67 | |
| LangGraphBase Model=Gemini-3.1-Flash-Lite, Framework Category=Commercial Framework (multi-agent mode)2026.04 | 36.67 | |
| MaASBase Model=GPT-OSS:120B, Framework Category=Adaptive topology methods2026.04 | 33.33 | |
| AgentDropoutBase Model=Gemini-3.1-Flash-Lite, Framework Category=Adaptive topology methods2026.04 | 33.33 | |
| AgentDropoutBase Model=GPT-OSS:120B, Framework Category=Adaptive topology methods2026.04 | 30 | |
| TopoDIMBase Model=GPT-OSS:120B, Framework Category=Adaptive topology methods2026.04 | 26.67 | |
| Base (direct)Base Model=GPT-OSS:120B, Framework Category=Single-agent baseline2026.04 | 20 | |
| LLM-DebateBase Model=Gemini-3.1-Flash-Lite, Framework Category=Static multi-agent2026.04 | 20 | |
| Base (direct)Base Model=Gemini-3.1-Flash-Lite, Framework Category=Single-agent baseline2026.04 | 13.33 |