Reasoning on Oolong real 2025 (test)
15.1ScoreDOLORES
Evaluation Results
| Method | Links | |
|---|---|---|
| DOLORESBase Model=Llama-3.3 70B Instruct2026.05 | 15.1 | |
| DOLORESBase Model=Qwen3 32B Thinking2026.05 | 13.2 | |
| CodeActBase Model=Llama-3.3 70B Instruct2026.05 | 7.9 | |
| RLMBase Model=Qwen3 32B Thinking2026.05 | 7.7 | |
| DOLORESBase Model=Qwen3 8B Thinking2026.05 | 7.6 | |
| RLMBase Model=Qwen3 8B Thinking2026.05 | 6.5 | |
| RLMBase Model=Llama-3.3 70B Instruct2026.05 | 6.4 | |
| CodeActBase Model=Qwen3 32B Thinking2026.05 | 6 | |
| CodeActBase Model=Qwen3 8B Thinking2026.05 | 4.5 |