List your company

General Tasks on MMLU-Pro

82.93AccuracyQwen3-Next-80B-A3B-Instruct
48.370857.342966.31575.2871Feb 19, 2025May 5, 2025Jul 19, 2025Oct 3, 2025Dec 17, 2025Mar 2, 2026May 17, 2026

Evaluation results

MethodLinks
Qwen3-Next-80B-A3B-InstructArchitecture=MoE, # Total Params=80B, # Activated Params=3B2026.0182.93
Gemini 2.5 Flash-Lite2026.0178.95
LongCat-Flash-LiteArchitecture=MoE + NE, # Total Params=68.5B, # Activated Params=2.9B~4.5B2026.0178.29
Llama-3.1-405BModel Type=Instruct, Parameters=405B2025.0273.3
Qwen2.5-VL-72BModel Type=Instruct, Parameters=72B2025.0271.2
Qwen2.5-72BModel Type=Instruct, Parameters=72B2025.0271.1
Kimi-Linear-48B-A3BArchitecture=MoE, # Total Params=48B, # Activated Params=3B2026.0167.22
Llama-3.1-70BModel Type=Instruct, Parameters=70B2025.0266.4
PODSModel=Qwen3-8B, Selection Ratio=50%2026.0566.4
Full DataModel=Qwen3-8B, Selection Ratio=100%2026.0565.8
Qwen2-72BModel Type=Instruct, Parameters=72B2025.0264.4
PODSModel=Qwen3-4B, Selection Ratio=50%2026.0561.5
Full DataModel=Qwen3-4B, Selection Ratio=100%2026.0561.1
Fine-tunedBase LLM=Qwen-2.5-7B-Instruct, Parameters=x42026.0555.6
DiDi-Merg.-LBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.02026.0555.2
FREE-MergingBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.082026.0554.8
Twin-MergingBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.252026.0554.5
Zero-shotBase LLM=Qwen-2.5-7B-Instruct, Parameters=x12026.0554
Fine-tunedBase LLM=Llama-3.1-8B-Instruct, Parameters=x42026.0551.3
DiDi-Merg.-LBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.02026.0551.1
FREE-MergingBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.082026.0550.4
Twin-MergingBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.252026.0550.2
Zero-shotBase LLM=Llama-3.1-8B-Instruct, Parameters=x12026.0549.7