General Artificial Intelligence Capabilities on Total Evaluation Suite (aggregate)
53.3Average ScoreSPOT
Evaluation Results
| Method | Links | |
|---|---|---|
| SPOTBackbone=Qwen3-8b2026.03 | 53.3 | |
| SFT+Backbone=Qwen3-8b2026.03 | 49.4 | |
| Qwen3-8bBackbone=Qwen3-8b2026.03 | 47.1 | |
| RFTBackbone=Qwen3-8b2026.03 | 46.4 | |
| SFTBackbone=Qwen3-8b2026.03 | 41.8 | |
| SPOTBackbone=Llama3.1-8b-Instruct2026.03 | 26 | |
| SFT+Backbone=Llama3.1-8b-Instruct2026.03 | 24.6 | |
| Llama3.1-8b-InstructBackbone=Llama3.1-8b-Instruct2026.03 | 24.3 | |
| RFTBackbone=Llama3.1-8b-Instruct2026.03 | 23.7 | |
| SFTBackbone=Llama3.1-8b-Instruct2026.03 | 22.4 |