---
base_model:
- CEIA-RL/energyv2-dpo-offline
---


|    | model_name                                      |   final_score |   task_coverage@1 |   relative_quality@1 |   hallucination@1 |
|---:|:------------------------------------------------|--------------:|------------------:|---------------------:|------------------:|
|  0 | qwen3-4b-dw-lr-dpo-offline-energy-GRPO_step_200 |     1.7964    |         0.970873  |            0.883589  |         0.0580614 |
|  1 | qwen3-4b-dw-lr-GRPO-mix-preference_step_100     |     1.77586   |         0.974856  |            0.875816  |         0.0748081 |
|  9 | energyv2-dpo-offline-GRPO_step_100              |     1.75576   |         0.957438  |            0.865499  |         0.0671785 |
|  4 | Qwen3-4B                                        |     1.73133   |         0.979511  |            0.872361  |         0.120537  |
| 10 | energyv2-dpo-offline-GRPO_step_180              |     1.66418   |         0.930302  |            0.826008  |         0.0921305 |
| 12 | energyv2-dpo-offline-GRPO_step_180_no_think     |     1.58354   |         0.946665  |            0.800216  |         0.16334   |
| 11 | energyv2-dpo-offline-GRPO_step_100_no_think     |     1.5715    |         0.939347  |            0.79333   |         0.16118   |
|  3 | qwen3-4b-dw-lr                                  |     1.52447   |         0.944386  |            0.782582  |         0.202495  |
|  2 | qwen3-4b-dw-lr-dpo-offline                      |     1.29638   |         0.785869  |            0.660269  |         0.14976   |
|  7 | energyv2-dpo-offline_think_off_                 |     0.940547  |         0.655758  |            0.515067  |         0.230278  |
|  8 | enregy-gpt-regulatorio-v2_think_off_            |     0.929175  |         0.826536  |            0.538196  |         0.435557  |
|  6 | energyv2-dpo-offline                            |    -0.0952015 |         0.0823417 |            0.0571017 |         0.234645  |
|  5 | enregy-gpt-regulatorio-v2                       |    -0.303599  |         0.303887  |            0.149664  |         0.75715   |


![img3](energy_v2_model_comparison_passk_only_2.png)

![img1](energy_v2_model_comparison_majk.png)

![img2](energy_v2_model_comparison_passk_only.png)