List your company

General Capability Evaluation on General Capability Suite

71Average ScoreTELLME
45.31251.98158.6565.319Feb 7, 2025

Evaluation results

MethodLinks
TELLMEBackbone=Qwen2.5-7B2025.0271
OriginBackbone=Qwen2.5-7B2025.0270.6
TELLME NT-XentBackbone=Qwen2.5-7B2025.0270
SFTBackbone=Qwen2.5-7B2025.0268.3
OriginBackbone=Llama-3.1-8B2025.0267.1
TELLME NT-XentBackbone=Llama-3.1-8B2025.0266.7
TELLMEBackbone=Llama-3.1-8B2025.0265.8
SFTBackbone=Llama-3.1-8B2025.0260.3
OriginBackbone=Mistral-7B-v0.32025.0251.6
TELLME NT-XentBackbone=Mistral-7B-v0.32025.0250.3
TELLMEBackbone=Mistral-7B-v0.32025.0249.6
SFTBackbone=Mistral-7B-v0.32025.0246.3