List your company

General Performance on Aggregated Benchmarks

49.76Overall AverageGeneral-Reasoner
27.86833.551539.23544.9185Jun 1, 2026

Evaluation results

MethodLinks
General-ReasonerGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0649.76
RESMERGEGroup=Qwen3-4B-Base, Category=Merged Models2026.0647.25
TAGroup=Qwen3-4B-Base, Category=Merged Models2026.0645.46
TSV-MergeGroup=Qwen3-4B-Base, Category=Merged Models2026.0645.07
GRPOGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0643.57
RAMGroup=Qwen3-4B-Base, Category=Merged Models2026.0642.22
RESMERGEBackbone=Qwen2.5-7B-Base, configuration=SRC-A+LHC2026.0641.08
ReasonerBackbone=Qwen2.5-7B-Base2026.0641.05
TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.0640.93
ISO-CBackbone=Qwen2.5-7B-Base2026.0638.86
ISO-CTSBackbone=Qwen2.5-7B-Base2026.0638.77
TABackbone=Qwen2.5-7B-Base2026.0638.66
SimpleRLBackbone=Qwen2.5-7B-Base2026.0638.57
SpiralGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0638.29
DARE + TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.0637.35
TSV-MergeBackbone=Qwen2.5-7B-Base2026.0635.39
Qwen2.5-7BBackbone=Qwen2.5-7B-Base2026.0634.32
TIESBackbone=Qwen2.5-7B-Base2026.0632.83
RAMBackbone=Qwen2.5-7B-Base2026.0631.7
DARE + TIESBackbone=Qwen2.5-7B-Base2026.0630.64
ZeroBackbone=Qwen2.5-7B-Base2026.0628.95
Qwen3-4BGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0628.71