List your company

Mathematical Reasoning on MATH lighteval

95.6AccuracyAgent 1 (Qwen3-30B-A3B-Instruct)
24.77643.16361.5579.937Sep 28, 2025Nov 4, 2025Dec 11, 2025Jan 17, 2026Feb 23, 2026Apr 1, 2026May 9, 2026

Evaluation results

MethodLinks
Agent 1 (Qwen3-30B-A3B-Instruct)Controller=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0595.6
Agent 1 (Qwen3-30B-A3B-Instruct)Controller=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0595.6
Iterative Critique-and-Routing ControllerController=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0591.5
Iterative Critique-and-Routing ControllerController=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0590.1
Controller V2Controller=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0588.3
GAPGModel=Qwen2.5-1.5B2025.0980.4
GAPGModel=LLaMA-3.2-3B2025.0979.5
RouterDCController=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0578.4
Router-R1Controller=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0577.6
RoBERTa RouterController=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0576.3
Controller V1Controller=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0576.1
Agent 2 (Qwen2.5-7B-Instruct)Controller=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0575.7
Random RouterController=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0575.6
Controller V2Controller=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0574.9
Router-R1Model=Qwen2.5-1.5B2025.0973.6
Router-R1Model=LLaMA-3.2-3B2025.0972.7
Agent 2 (Ministral-3-8B-Instruct)Controller=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0572.4
Router-R1Controller=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0568.6
RouterDCController=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0568.1
Random RouterController=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0567
RoBERTa RouterController=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0565.9
Controller V1Controller=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0562.6
AutoMixModel=Qwen2.5-1.5B2025.0959.4
Agent 3 (Qwen2.5-1.5B-Instruct)Controller=Qwen2.5-7B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Qwen2.5-7B-Instruct, Agent 3=Qwen2.5-1.5B-Instruct2026.0555.4
AutoMixModel=LLaMA-3.2-3B2025.0955.3
Agent 3 (Llama-3-2-1B-Instruct)Controller=Qwen3-4B-Base, Agent 1=Qwen3-30B-A3B-Instruct, Agent 2=Ministral-3-8B-Instruct, Agent 3=Llama-3-2-1B-Instruct2026.0527.5