List your company

Language Understanding on MMLU CF

74.5ScoreCAP-CoT
64.72467.26269.872.338Feb 10, 2026Feb 22, 2026Mar 6, 2026Mar 19, 2026Mar 31, 2026Apr 12, 2026Apr 25, 2026

Evaluation results

MethodLinks
CAP-CoTBackbone=GPT-4o2026.0474.5
ToTBackbone=GPT-4o2026.0473.5
ECONBackbone=GPT-4o2026.0473.5
MADBackbone=GPT-4o2026.0473
AoTBackbone=GPT-4o2026.0473
CoT-SCBackbone=GPT-4o2026.0472.8
CAP-CoTBackbone=GPT-4o-mini2026.0472.5
FoTBackbone=GPT-4o2026.0472.4
PromptAgentBackbone=GPT-4o2026.0472.3
CAP-CoTBackbone=Deepseek-V32026.0472.2
GoTBackbone=GPT-4o2026.0472.2
CCoTBackbone=GPT-4o2026.0472.1
ToTBackbone=Deepseek-V32026.0472
ECONBackbone=Deepseek-V32026.0471.8
Self-RefineBackbone=GPT-4o2026.0471.8
GoTBackbone=GPT-4o-mini2026.0471.6
CAP-CoTBackbone=Qwen-turbo2026.0471.6
ECONBackbone=GPT-4o-mini2026.0471.5
CoT-SCBackbone=Deepseek-V32026.0471.5
CoTBackbone=GPT-4o2026.0471.5
ToTBackbone=Qwen-turbo2026.0471.3
ECONBackbone=Qwen-turbo2026.0471.2
MADBackbone=Deepseek-V32026.0471.2
AFlowBackbone=GPT-4o2026.0471.2
CoT-SCBackbone=GPT-4o-mini2026.0471.1
MADBackbone=GPT-4o-mini2026.0471
AoTBackbone=GPT-4o-mini2026.0470.9
CoT-SCBackbone=Qwen-turbo2026.0470.8
MADBackbone=Qwen-turbo2026.0470.8
AoTBackbone=Deepseek-V32026.0470.8
FoTBackbone=GPT-4o-mini2026.0470.6
PromptAgentBackbone=Deepseek-V32026.0470.6
PromptAgentBackbone=GPT-4o-mini2026.0470.5
AoTBackbone=Qwen-turbo2026.0470.5
FoTBackbone=Deepseek-V32026.0470.5
CCoTBackbone=GPT-4o-mini2026.0470.4
FoTBackbone=Qwen-turbo2026.0470.4
GoTBackbone=Deepseek-V32026.0470.3
ToTBackbone=GPT-4o-mini2026.0470.2
PromptAgentBackbone=Qwen-turbo2026.0470.1
CCoTBackbone=Qwen-turbo2026.0470.1
GoTBackbone=Qwen-turbo2026.0470.1
Self-RefineBackbone=Deepseek-V32026.0470.1
CCoTBackbone=Deepseek-V32026.0470.1
CoTBackbone=Deepseek-V32026.0469.9
GHS-TDABackbone=Qwen 2-14B2026.0269.8
AFlowBackbone=Deepseek-V32026.0469.8
Self-RefineBackbone=GPT-4o-mini2026.0469.7
CoTBackbone=GPT-4o-mini2026.0469.6
AFlowBackbone=GPT-4o-mini2026.0469.5
Self-RefineBackbone=Qwen-turbo2026.0469.5
CoTBackbone=Qwen-turbo2026.0469.4
AFlowBackbone=Qwen-turbo2026.0469.3
AoTBackbone=Qwen 2-14B2026.0268.9
GoTBackbone=Qwen 2-14B2026.0267.8
ToTBackbone=Qwen 2-14B2026.0267.6
APBackbone=GPT-4o2026.0467.5
GHS-TDABackbone=Llama 3-8B2026.0267.3
AoTBackbone=Llama 3-8B2026.0266.65
APBackbone=Deepseek-V32026.0466.1
GoTBackbone=Llama 3-8B2026.0265.99
APBackbone=GPT-4o-mini2026.0465.8
ToTBackbone=Llama 3-8B2026.0265.71
CoTBackbone=Llama 3-8B2026.0265.42
APBackbone=Qwen-turbo2026.0465.2
CoTBackbone=Qwen 2-14B2026.0265.1