General Capability Evaluation on General Capability Suite
71Average ScoreTELLME
Evaluation Results
| Method | Links | |
|---|---|---|
| TELLMEBackbone=Qwen2.5-7B2025.02 | 71 | |
| OriginBackbone=Qwen2.5-7B2025.02 | 70.6 | |
| TELLME NT-XentBackbone=Qwen2.5-7B2025.02 | 70 | |
| SFTBackbone=Qwen2.5-7B2025.02 | 68.3 | |
| OriginBackbone=Llama-3.1-8B2025.02 | 67.1 | |
| TELLME NT-XentBackbone=Llama-3.1-8B2025.02 | 66.7 | |
| TELLMEBackbone=Llama-3.1-8B2025.02 | 65.8 | |
| SFTBackbone=Llama-3.1-8B2025.02 | 60.3 | |
| OriginBackbone=Mistral-7B-v0.32025.02 | 51.6 | |
| TELLME NT-XentBackbone=Mistral-7B-v0.32025.02 | 50.3 | |
| TELLMEBackbone=Mistral-7B-v0.32025.02 | 49.6 | |
| SFTBackbone=Mistral-7B-v0.32025.02 | 46.3 |