List your company

Code Generation on HumanEval++

98.44AccuracyAFlow
5.526429.648253.7777.8918Nov 11, 2025Nov 28, 2025Dec 15, 2025Jan 2, 2026Jan 19, 2026Feb 5, 2026Feb 23, 2026

Evaluation results

MethodLinks
AFlowMulti=true, Topo=true, Role=false, Node=false, Backbone=Qwen3-80B2026.0298.44
MASRouterMulti=true, Topo=true, Role=true, Node=false, Backbone=Qwen3-80B2026.0298.44
MASRouterMulti=true, Topo=true, Role=true, Node=false, Backbone=GPT-5-Mini2026.0296.88
HieraMASMulti=true, Topo=true, Role=true, Node=true, Backbone=Qwen3-80B2026.0296.88
AFlowMulti=true, Topo=true, Role=false, Node=false, Backbone=GPT-5-Mini2026.0295.31
GDesignerMulti=true, Topo=true, Role=false, Node=false, Backbone=Qwen3-80B2026.0293.75
HieraMASMulti=true, Topo=true, Role=true, Node=true, Backbone=GPT-5-Mini2026.0293.75
Full-GraphMulti=true, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0292.19
Random-GraphMulti=true, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0292.19
Self-Consistency+CoTMulti=true, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0290.62
GDesignerMulti=true, Topo=true, Role=false, Node=false, Backbone=GPT-5-Mini2026.0290.62
BaseMulti=false, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0289.06
Self-ConsistencyMulti=true, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0289.06
Full-GraphMulti=true, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0289.06
CoTMulti=false, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0287.5
Self-ConsistencyMulti=true, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0287.5
LLM-DebateMulti=true, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0287.5
LLM-DebateMulti=true, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0287.5
CoTMulti=false, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0285.94
Self-Consistency+CoTMulti=true, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0285.94
Random-GraphMulti=true, Topo=false, Role=false, Node=false, Backbone=GPT-5-Mini2026.0285.94
BaseMulti=false, Topo=false, Role=false, Node=false, Backbone=Qwen3-80B2026.0284.14
TaH+Model Size=4B*2025.1172
OuroModel Size=4B*2025.1170.7
TaHModel Size=4B*2025.1170.1
StandardModel Size=4B*2025.1169.2
SoftThinkModel Size=4B*2025.1169.2
TaH+Model Size=1.7B2025.1151.5
TaHModel Size=1.7B2025.1150
SoftThinkModel Size=1.7B2025.1143.3
OuroModel Size=1.7B2025.1140.9
StandardModel Size=1.7B2025.1139
TaH+Model Size=0.6B2025.1122
TaHModel Size=0.6B2025.1121.6
OuroModel Size=0.6B2025.1118.9
StandardModel Size=0.6B2025.1116.8
AlwaysThinkModel Size=1.7B2025.1116.4
SoftThinkModel Size=0.6B2025.1114.3
AlwaysThinkModel Size=0.6B2025.119.1