Open-book Question Answering on OpenBookQA 1.0 (test)
35AccuracyTituLLM-3b-v2.0
Evaluation results
| Method | Links | |
|---|---|---|
| TituLLM-3b-v2.0Shots=52025.02 | 35 | |
| Gemma-2-2bShots=02025.02 | 34 | |
| Gemma-2-2bShots=52025.02 | 33 | |
| BLOOM-3bShots=02025.02 | 33 | |
| BongLLaMA-3.2-1bShots=02025.02 | 33 | |
| TituLLM-1b-v2.0Shots=52025.02 | 33 | |
| Llama-3.2-1bShots=02025.02 | 32 | |
| Llama-3.2-1bShots=52025.02 | 32 | |
| Llama-3.2-3bShots=02025.02 | 32 | |
| Llama-3.2-3bShots=52025.02 | 32 | |
| BLOOM-1b7Shots=02025.02 | 32 | |
| TituLLM-1b-v2.0Shots=02025.02 | 32 | |
| TituLLM-3b-v2.0Shots=02025.02 | 32 | |
| Qwen-2.5-0.5bShots=02025.02 | 31 | |
| SmolLM2-135mShots=02025.02 | 31 | |
| SmolLM2-1.7bShots=02025.02 | 31 | |
| BLOOM-560mShots=02025.02 | 31 | |
| BLOOM-1b1Shots=02025.02 | 31 | |
| BLOOM-1b1Shots=52025.02 | 31 | |
| BLOOM-1b7Shots=52025.02 | 31 | |
| BLOOM-3bShots=52025.02 | 31 | |
| BongLLaMA-3.2-1bShots=52025.02 | 31 | |
| davinciShots=02025.02 | 30 | |
| Qwen-2.5-0.5bShots=52025.02 | 30 | |
| Qwen-2.5-1.5bShots=52025.02 | 30 | |
| SmolLM2-135mShots=52025.02 | 30 | |
| SmolLM2-360mShots=02025.02 | 30 | |
| SmolLM2-1.7bShots=52025.02 | 30 | |
| Qwen-2.5-1.5bShots=02025.02 | 29 | |
| SmolLM2-360mShots=52025.02 | 29 | |
| BongLLaMA-3.2-3bShots=52025.02 | 29 | |
| BLOOM-560mShots=52025.02 | 28 | |
| BongLLaMA-3.2-3bShots=02025.02 | 27 |