Minimum Coloring on min-coloring
24.1FeasibilityLlama-8b SFT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Llama-8b SFTSampling strategy=BestOf8, Training=SFT, Backbone=Llama-8b2026.04 | 24.1 | 10.04 | 2.06 | |
| GPT5.2Model=GPT5.22026.04 | 22.2 | 70.58 | 17.04 | |
| Llama-8b SFTSampling strategy=BestOf1, Training=SFT, Backbone=Llama-8b2026.04 | 10.1 | 16.64 | 3.9 |