Question Answering on BBH
94.6AccuracyGemini
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Geminimode=Single-turn2026.02 | 94.6 | — | |
| OursOmode=Single-turn2026.02 | 76 | — | |
| OursImode=Single-turn2026.02 | 75.8 | — | |
| GPTmode=Single-turn2026.02 | 70.8 | — | |
| LLaMA-3-70B-Instruct2025.06 | 58.01 | — | |
| RCOBase Model=LLaMA-3-8B-Instruct2025.06 | 53.51 | — | |
| Qwenmode=Single-turn2026.02 | 50.6 | — | |
| RCOBase Model=UltraCM-13B2025.06 | 49.75 | — | |
| RCOBase Model=LLaMA-2-7B-Chat2025.06 | 48.06 | — | |
| RCOBase Model=LLaMA-2-13B-Chat2025.06 | 47.89 | — | |
| DPCOBase Model=UltraCM-13B2025.06 | 47.29 | — | |
| RCOBase Model=Auto-J-13B2025.06 | 46.18 | — | |
| UltraCM-13B2025.06 | 45.93 | — | |
| DPCOBase Model=LLaMA-2-7B-Chat2025.06 | 45.52 | — | |
| DPCOBase Model=LLaMA-3-8B-Instruct2025.06 | 45.37 | — | |
| LLaMA-3-8B-Instruct2025.06 | 45.33 | — | |
| mPLUG-Owl2Shot setting=0-shot2023.11 | 45 | — | |
| LLAMA-2-70B-Chat2025.06 | 44.19 | — | |
| Self-refinement2025.06 | 43.65 | — | |
| DPCOBase Model=LLaMA-2-13B-Chat2025.06 | 43.41 | — | |
| DPCOBase Model=Auto-J-13B2025.06 | 43.22 | — | |
| Aligner2025.06 | 42.39 | — | |
| Vicuna-v1.5Shot setting=0-shot2023.11 | 41.2 | — | |
| LLaMA-2-13B-Chat2025.06 | 40.3 | — | |
| Initial Answer2025.06 | 39.67 | — | |
| SPD-QABackbone=Qwen2.5-0.5B-Instruct, Calibration Domain=QA2026.05 | 38.7 | — | |
| LLaMA-2-7B-Chat2025.06 | 38.22 | — | |
| LLaMA-2Shot setting=0-shot2023.11 | 38.2 | — | |
| Auto-J-13B2025.06 | 37.75 | — | |
| SSD-QABackbone=Qwen2.5-0.5B-Instruct, Calibration Domain=QA2026.05 | 36 | — | |
| LLaMA-2-ChatShot setting=0-shot2023.11 | 35.6 | — | |
| WizardLMShot setting=0-shot2023.11 | 34.7 | — | |
| Base modelBackbone=Qwen2.5-0.5B-Instruct2026.05 | 32.7 | — | |
| Base modelBackbone=Qwen2.5-0.5B-Instruct2026.05 | — | 32.7 | |
| Base modelBackbone=Qwen2.5-7B-Instruct2026.05 | — | 47.3 | |
| Base modelBackbone=Qwen2.5-14B-Instruct2026.05 | — | 54 | |
| Base modelBackbone=Qwen3-4B-Instruct2026.05 | — | 49 | |
| Base modelBackbone=Llama-3.1-8B-Instruct2026.05 | — | 59 | |
| PSRBackbone=Qwen2.5-0.5B-Instruct2026.05 | — | 33.7 | |
| PSRBackbone=Qwen2.5-7B-Instruct2026.05 | — | 48.3 | |
| PSRBackbone=Qwen2.5-14B-Instruct2026.05 | — | 55.3 | |
| PSRBackbone=Qwen3-4B-Instruct2026.05 | — | 48.7 | |
| PSRBackbone=Llama-3.1-8B-Instruct2026.05 | — | 56.7 | |
| SPDBackbone=Qwen2.5-0.5B-Instruct2026.05 | — | 38.7 | |
| SPDBackbone=Qwen2.5-7B-Instruct2026.05 | — | 50.3 | |
| SPDBackbone=Qwen2.5-14B-Instruct2026.05 | — | 54.7 | |
| SPDBackbone=Qwen3-4B-Instruct2026.05 | — | 49.3 | |
| SPDBackbone=Llama-3.1-8B-Instruct2026.05 | — | 57.3 | |
| SSDBackbone=Qwen2.5-0.5B-Instruct2026.05 | — | 36 | |
| SSDBackbone=Qwen2.5-7B-Instruct2026.05 | — | 50 | |
| SSDBackbone=Qwen2.5-14B-Instruct2026.05 | — | 54 | |
| SSDBackbone=Qwen3-4B-Instruct2026.05 | — | 48 | |
| SSDBackbone=Llama-3.1-8B-Instruct2026.05 | — | 56.7 |