List your company

Multi-task Language Understanding on MMLUpro (test)

95.71AccuracySIGMA
11.771633.563355.35577.1467Jan 24, 2025Apr 14, 2025Jul 3, 2025Sep 21, 2025Dec 10, 2025Feb 28, 2026May 19, 2026

Evaluation results

MethodLinks
SIGMAMulti-agent collaboration=full support, Inter-agent relations=full support, Handling conflicting signals=full support2026.0595.71
G-DesignerMulti-agent collaboration=full support, Inter-agent relations=full support2026.0595.31
GoAMulti-agent collaboration=full support, Inter-agent relations=full support2026.0595.1
GPTSwarmMulti-agent collaboration=full support, Inter-agent relations=full support2026.0594.87
Complete GraphMulti-agent collaboration=full support, Inter-agent relations=full support, Handling conflicting signals=no support2026.0594.73
Random GraphMulti-agent collaboration=full support, Inter-agent relations=full support, Handling conflicting signals=no support2026.0593.42
AutoGenMulti-agent collaboration=full support, Inter-agent relations=full support2026.0593.29
SCMulti-agent collaboration=no support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0591.43
DyLANMulti-agent collaboration=full support, Inter-agent relations=full support2026.0591.43
PHPMulti-agent collaboration=full support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0591.32
ComplexCoTMulti-agent collaboration=no support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0588.76
Self-MoAMulti-agent collaboration=full support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0588.69
MoAMulti-agent collaboration=full support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0588.57
CoTMulti-agent collaboration=no support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0587.58
VanillaMulti-agent collaboration=no support, Inter-agent relations=no support, Handling conflicting signals=no support2026.0584.17
GPT-3.52025.0174.8
SID-vModel=GPT-OSS-20B2025.1071
SID-cModel=GPT-OSS-20B2025.1070
Self-ConsistencyModel=GPT-OSS-20B2025.1069
Self-ContrastModel=GPT-OSS-20B2025.1065
DMADModel=GPT-OSS-20B2025.1065
IOModel=GPT-OSS-20B2025.1064
GPT-42025.0163.71
COTModel=GPT-OSS-20B2025.1061
SID-vModel=LLaMA3.1-8B2025.1047
SID-cModel=LLaMA3.1-8B2025.1047
Self-ConsistencyModel=LLaMA3.1-8B2025.1045
MADModel=LLaMA3.1-8B2025.1041
COTModel=LLaMA3.1-8B2025.1039
DMADModel=LLaMA3.1-8B2025.1039
Self-ContrastModel=LLaMA3.1-8B2025.1036
TAMA2025.0131.84
SBPModel=GPT-OSS-20B2025.1026
IOModel=LLaMA3.1-8B2025.1025
base2025.0122.1
SBPModel=LLaMA3.1-8B2025.1015