Question Answering on GPQA (ANLL, NLL, SC, CE, RDSs, RDSsw)
19.7ANLLANLL
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| ANLLModel=Llama3.22025.12 | 19.7 | — | — | — | — | — | |
| ANLLModel=Llama3.12025.12 | 20.7 | — | — | — | — | — | |
| ANLLModel=Gemma22025.12 | 23.8 | — | — | — | — | — | |
| ANLLModel=Falcon32025.12 | 28 | — | — | — | — | — | |
| CEModel=Falcon32025.12 | — | — | — | 22.8 | — | — | |
| CEModel=Gemma22025.12 | — | — | — | 19.2 | — | — | |
| CEModel=Llama3.12025.12 | — | — | — | 18.1 | — | — | |
| CEModel=Llama3.22025.12 | — | — | — | 22.8 | — | — | |
| NLLModel=Falcon32025.12 | — | 24.4 | — | — | — | — | |
| NLLModel=Gemma22025.12 | — | 20.7 | — | — | — | — | |
| NLLModel=Llama3.12025.12 | — | 20.2 | — | — | — | — | |
| NLLModel=Llama3.22025.12 | — | 20.2 | — | — | — | — | |
| RDSsModel=Falcon32025.12 | — | — | — | — | 26.4 | — | |
| RDSsModel=Gemma22025.12 | — | — | — | — | 24.4 | — | |
| RDSsModel=Llama3.12025.12 | — | — | — | — | 23.8 | — | |
| RDSsModel=Llama3.22025.12 | — | — | — | — | 22.8 | — | |
| RDSswModel=Falcon32025.12 | — | — | — | — | — | 28.5 | |
| RDSswModel=Gemma22025.12 | — | — | — | — | — | 25.9 | |
| RDSswModel=Llama3.12025.12 | — | — | — | — | — | 26.4 | |
| RDSswModel=Llama3.22025.12 | — | — | — | — | — | 23.8 | |
| SCModel=Falcon32025.12 | — | — | 22.8 | — | — | — | |
| SCModel=Gemma22025.12 | — | — | 19.2 | — | — | — | |
| SCModel=Llama3.12025.12 | — | — | 17.6 | — | — | — | |
| SCModel=Llama3.22025.12 | — | — | 16.6 | — | — | — |