Update contamination_report.csv
Browse filesAdd all contaminations > 3% instead of >50% from Table 3
- contamination_report.csv +11 -0
contamination_report.csv
CHANGED
|
@@ -465,4 +465,15 @@ RadNLI;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
|
|
| 465 |
|
| 466 |
|
| 467 |
cais/mmlu;;GPT-3.5;model;;;52.0;model-based;https://arxiv.org/abs/2311.09783;10
|
|
|
|
|
|
|
|
|
|
| 468 |
cais/mmlu;;GPT-4;model;;;57.0;model-based;https://arxiv.org/abs/2311.09783;10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 465 |
|
| 466 |
|
| 467 |
cais/mmlu;;GPT-3.5;model;;;52.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 468 |
+
winogrande;;GPT-3.5;model;;;9.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 469 |
+
truthful_qa;;GPT-3.5;model;;;12.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 470 |
+
|
| 471 |
cais/mmlu;;GPT-4;model;;;57.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 472 |
+
truthful_qa;;GPT-4;model;;;10.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 473 |
+
winogrande;;GPT-4;model;;;12.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 474 |
+
|
| 475 |
+
allenai/openbookqa;;LLaMa 2-13B;model;;;4.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 476 |
+
|
| 477 |
+
truthful_qa;;Mistral-7B;model;;;15.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 478 |
+
allenai/openbookqa;;Mistral-7B;model;;;10.0;model-based;https://arxiv.org/abs/2311.09783;10
|
| 479 |
+
winogrande;;Mistral-7B;model;;;3.0;model-based;https://arxiv.org/abs/2311.09783;10
|