Spaces:
Sleeping
Sleeping
update leaderboard.json
Browse files- leaderboard.json +139 -27
leaderboard.json
CHANGED
|
@@ -2,13 +2,21 @@
|
|
| 2 |
{
|
| 3 |
"ID": 1,
|
| 4 |
"Category": "RA",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"Benchmark": "ARC_deepseek_r1_denoising",
|
| 6 |
"WAR": 0.00,
|
| 7 |
"SED": 0.67,
|
| 8 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/ARC/arc_deepseek_r1_denoising)"
|
| 9 |
},
|
| 10 |
{
|
| 11 |
-
"ID":
|
| 12 |
"Category": "RA",
|
| 13 |
"Benchmark": "ARC_wac_gec",
|
| 14 |
"WAR": 0.00,
|
|
@@ -16,7 +24,15 @@
|
|
| 16 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/ARC/arc_wac_gec)"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"Category": "TG",
|
| 21 |
"Benchmark": "COQA_deepseek_r1_denoising",
|
| 22 |
"WAR": 4.18,
|
|
@@ -24,7 +40,7 @@
|
|
| 24 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/COQA/coqa_deepseek_r1_denoising)"
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"ID":
|
| 28 |
"Category": "TG",
|
| 29 |
"Benchmark": "COQA_wac_gec",
|
| 30 |
"WAR": 4.70,
|
|
@@ -32,7 +48,15 @@
|
|
| 32 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/COQA/coqa_wac_gec)"
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"Category": "TG",
|
| 37 |
"Benchmark": "DROP_deepseek_r1_denoising",
|
| 38 |
"WAR": 0.02,
|
|
@@ -40,7 +64,7 @@
|
|
| 40 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/DROP/drop_deepseek_r1_denoising)"
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"ID":
|
| 44 |
"Category": "TG",
|
| 45 |
"Benchmark": "DROP_wac_gec",
|
| 46 |
"WAR": 0.64,
|
|
@@ -48,7 +72,15 @@
|
|
| 48 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/DROP/drop_wac_gec)"
|
| 49 |
},
|
| 50 |
{
|
| 51 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"Category": "BT",
|
| 53 |
"Benchmark": "MRPC_deepseek_r1_denoising",
|
| 54 |
"WAR": 3.80,
|
|
@@ -56,7 +88,7 @@
|
|
| 56 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/mrpc)"
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"ID":
|
| 60 |
"Category": "BT",
|
| 61 |
"Benchmark": "MRPC_wac_gec",
|
| 62 |
"WAR": 1.84,
|
|
@@ -64,7 +96,15 @@
|
|
| 64 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/mrpc)"
|
| 65 |
},
|
| 66 |
{
|
| 67 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
"Category": "BT",
|
| 69 |
"Benchmark": "RTE_deepseek_r1_denoising",
|
| 70 |
"WAR": 0.36,
|
|
@@ -72,7 +112,7 @@
|
|
| 72 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/rte)"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"ID":
|
| 76 |
"Category": "BT",
|
| 77 |
"Benchmark": "RTE_wac_gec",
|
| 78 |
"WAR": 0.72,
|
|
@@ -80,7 +120,15 @@
|
|
| 80 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/rte)"
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
"Category": "BT",
|
| 85 |
"Benchmark": "SST2_deepseek_r1_denoising",
|
| 86 |
"WAR": 7.22,
|
|
@@ -88,7 +136,7 @@
|
|
| 88 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/sst2)"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"ID":
|
| 92 |
"Category": "BT",
|
| 93 |
"Benchmark": "SST2_wac_gec",
|
| 94 |
"WAR": 5.39,
|
|
@@ -96,7 +144,15 @@
|
|
| 96 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/sst2)"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
"Category": "SU",
|
| 101 |
"Benchmark": "WNLI_deepseek_r1_denoising",
|
| 102 |
"WAR": 0.00,
|
|
@@ -104,7 +160,7 @@
|
|
| 104 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/wnli)"
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"ID":
|
| 108 |
"Category": "SU",
|
| 109 |
"Benchmark": "WNLI_wac_gec",
|
| 110 |
"WAR": 0.00,
|
|
@@ -112,7 +168,15 @@
|
|
| 112 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/wnli)"
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
"Category": "RA",
|
| 117 |
"Benchmark": "GSM8K_deepseek_r1_denoising",
|
| 118 |
"WAR": 0.30,
|
|
@@ -120,7 +184,7 @@
|
|
| 120 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GSM8K/gsm8k_deepseek_r1_denoising)"
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"ID":
|
| 124 |
"Category": "RA",
|
| 125 |
"Benchmark": "GSM8K_wac_gec",
|
| 126 |
"WAR": 1.97,
|
|
@@ -128,7 +192,15 @@
|
|
| 128 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GSM8K/gsm8k_wac_gec)"
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
"Category": "RA",
|
| 133 |
"Benchmark": "MMLU_deepseek_r1_denoising",
|
| 134 |
"WAR": 6.56,
|
|
@@ -136,7 +208,7 @@
|
|
| 136 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MMLU/mmlu_deepseek_r1_denoising)"
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"ID":
|
| 140 |
"Category": "RA",
|
| 141 |
"Benchmark": "MMLU_wac_gec",
|
| 142 |
"WAR": 2.98,
|
|
@@ -144,7 +216,15 @@
|
|
| 144 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MMLU/mmlu_wac_gec)"
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
"Category": "ME",
|
| 149 |
"Benchmark": "MedMCQA_deepseek_r1_denoising",
|
| 150 |
"WAR": 3.44,
|
|
@@ -152,7 +232,7 @@
|
|
| 152 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedMCQA/medmcqa_deepseek_r1_denoising)"
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"ID":
|
| 156 |
"Category": "ME",
|
| 157 |
"Benchmark": "MedMCQA_wac_gec",
|
| 158 |
"WAR": 2.44,
|
|
@@ -160,7 +240,15 @@
|
|
| 160 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedMCQA/medmcqa_wac_gec)"
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 164 |
"Category": "ME",
|
| 165 |
"Benchmark": "MedQA_deepseek_r1_denoising",
|
| 166 |
"WAR": 16.26,
|
|
@@ -168,7 +256,7 @@
|
|
| 168 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedQA/MedQA_deepseek_r1_denoising)"
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"ID":
|
| 172 |
"Category": "ME",
|
| 173 |
"Benchmark": "MedQA_wac_gec",
|
| 174 |
"WAR": 0.79,
|
|
@@ -176,7 +264,15 @@
|
|
| 176 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedQA/MedQA_wac_gec)"
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
"Category": "SU",
|
| 181 |
"Benchmark": "Natural_questions_deepseek_r1_denoising",
|
| 182 |
"WAR": 0.06,
|
|
@@ -184,7 +280,7 @@
|
|
| 184 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Natural_questions/nq_open_deepseek_r1_denoising)"
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"ID":
|
| 188 |
"Category": "SU",
|
| 189 |
"Benchmark": "Natural_questions_wac_gec",
|
| 190 |
"WAR": 0.28,
|
|
@@ -192,7 +288,15 @@
|
|
| 192 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Natural_questions/nq_open_wac_gec)"
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 196 |
"Category": "ME",
|
| 197 |
"Benchmark": "PubMedQA_deepseek_r1_denoising",
|
| 198 |
"WAR": 0.20,
|
|
@@ -200,7 +304,7 @@
|
|
| 200 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/PubMedQA/pubmed_qa_deepseek_r1_denoising)"
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"ID":
|
| 204 |
"Category": "ME",
|
| 205 |
"Benchmark": "PubMedQA_wac_gec",
|
| 206 |
"WAR": 0.00,
|
|
@@ -208,7 +312,15 @@
|
|
| 208 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/PubMedQA/pubmed_qa_wac_gec)"
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"ID":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
"Category": "TG",
|
| 213 |
"Benchmark": "Truthful_QA_deepseek_r1_denoising",
|
| 214 |
"WAR": 0.00,
|
|
@@ -216,7 +328,7 @@
|
|
| 216 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Truthful_QA/truthful_qa_deepseek_r1_denoising)"
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"ID":
|
| 220 |
"Category": "TG",
|
| 221 |
"Benchmark": "Truthful_QA_wac_gec",
|
| 222 |
"WAR": 0.00,
|
|
|
|
| 2 |
{
|
| 3 |
"ID": 1,
|
| 4 |
"Category": "RA",
|
| 5 |
+
"Benchmark": "ARC",
|
| 6 |
+
"WAR": 0.11,
|
| 7 |
+
"SED": 0.67,
|
| 8 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/ARC/arc)"
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"ID": 2,
|
| 12 |
+
"Category": "RA",
|
| 13 |
"Benchmark": "ARC_deepseek_r1_denoising",
|
| 14 |
"WAR": 0.00,
|
| 15 |
"SED": 0.67,
|
| 16 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/ARC/arc_deepseek_r1_denoising)"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"ID": 3,
|
| 20 |
"Category": "RA",
|
| 21 |
"Benchmark": "ARC_wac_gec",
|
| 22 |
"WAR": 0.00,
|
|
|
|
| 24 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/ARC/arc_wac_gec)"
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"ID": 4,
|
| 28 |
+
"Category": "TG",
|
| 29 |
+
"Benchmark": "COQA",
|
| 30 |
+
"WAR": 6.79,
|
| 31 |
+
"SED": 2.74,
|
| 32 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/COQA/coqa)"
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"ID": 5,
|
| 36 |
"Category": "TG",
|
| 37 |
"Benchmark": "COQA_deepseek_r1_denoising",
|
| 38 |
"WAR": 4.18,
|
|
|
|
| 40 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/COQA/coqa_deepseek_r1_denoising)"
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"ID": 6,
|
| 44 |
"Category": "TG",
|
| 45 |
"Benchmark": "COQA_wac_gec",
|
| 46 |
"WAR": 4.70,
|
|
|
|
| 48 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/COQA/coqa_wac_gec)"
|
| 49 |
},
|
| 50 |
{
|
| 51 |
+
"ID": 7,
|
| 52 |
+
"Category": "TG",
|
| 53 |
+
"Benchmark": "DROP",
|
| 54 |
+
"WAR": 1.50,
|
| 55 |
+
"SED": 3.38,
|
| 56 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/DROP/drop)"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"ID": 8,
|
| 60 |
"Category": "TG",
|
| 61 |
"Benchmark": "DROP_deepseek_r1_denoising",
|
| 62 |
"WAR": 0.02,
|
|
|
|
| 64 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/DROP/drop_deepseek_r1_denoising)"
|
| 65 |
},
|
| 66 |
{
|
| 67 |
+
"ID": 9,
|
| 68 |
"Category": "TG",
|
| 69 |
"Benchmark": "DROP_wac_gec",
|
| 70 |
"WAR": 0.64,
|
|
|
|
| 72 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/DROP/drop_wac_gec)"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"ID": 10,
|
| 76 |
+
"Category": "BT",
|
| 77 |
+
"Benchmark": "MRPC",
|
| 78 |
+
"WAR": 100.00,
|
| 79 |
+
"SED": 5.65,
|
| 80 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue/mrpc)"
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"ID": 11,
|
| 84 |
"Category": "BT",
|
| 85 |
"Benchmark": "MRPC_deepseek_r1_denoising",
|
| 86 |
"WAR": 3.80,
|
|
|
|
| 88 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/mrpc)"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"ID": 12,
|
| 92 |
"Category": "BT",
|
| 93 |
"Benchmark": "MRPC_wac_gec",
|
| 94 |
"WAR": 1.84,
|
|
|
|
| 96 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/mrpc)"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"ID": 13,
|
| 100 |
+
"Category": "BT",
|
| 101 |
+
"Benchmark": "RTE",
|
| 102 |
+
"WAR": 2.17,
|
| 103 |
+
"SED": 4.47,
|
| 104 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue/rte)"
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"ID": 14,
|
| 108 |
"Category": "BT",
|
| 109 |
"Benchmark": "RTE_deepseek_r1_denoising",
|
| 110 |
"WAR": 0.36,
|
|
|
|
| 112 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/rte)"
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"ID": 15,
|
| 116 |
"Category": "BT",
|
| 117 |
"Benchmark": "RTE_wac_gec",
|
| 118 |
"WAR": 0.72,
|
|
|
|
| 120 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/rte)"
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"ID": 16,
|
| 124 |
+
"Category": "BT",
|
| 125 |
+
"Benchmark": "SST2",
|
| 126 |
+
"WAR": 98.97,
|
| 127 |
+
"SED": 5.42,
|
| 128 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue/sst2)"
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"ID": 17,
|
| 132 |
"Category": "BT",
|
| 133 |
"Benchmark": "SST2_deepseek_r1_denoising",
|
| 134 |
"WAR": 7.22,
|
|
|
|
| 136 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/sst2)"
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"ID": 18,
|
| 140 |
"Category": "BT",
|
| 141 |
"Benchmark": "SST2_wac_gec",
|
| 142 |
"WAR": 5.39,
|
|
|
|
| 144 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/sst2)"
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"ID": 19,
|
| 148 |
+
"Category": "SU",
|
| 149 |
+
"Benchmark": "WNLI",
|
| 150 |
+
"WAR": 0.70,
|
| 151 |
+
"SED": 0.64,
|
| 152 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue/wnli)"
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"ID": 20,
|
| 156 |
"Category": "SU",
|
| 157 |
"Benchmark": "WNLI_deepseek_r1_denoising",
|
| 158 |
"WAR": 0.00,
|
|
|
|
| 160 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_deepseek_r1_denoising/wnli)"
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"ID": 21,
|
| 164 |
"Category": "SU",
|
| 165 |
"Benchmark": "WNLI_wac_gec",
|
| 166 |
"WAR": 0.00,
|
|
|
|
| 168 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GLUE/glue_wac_gec/wnli)"
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"ID": 22,
|
| 172 |
+
"Category": "RA",
|
| 173 |
+
"Benchmark": "GSM8K",
|
| 174 |
+
"WAR": 25.70,
|
| 175 |
+
"SED": 1.11,
|
| 176 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GSM8K/gsm8k)"
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"ID": 23,
|
| 180 |
"Category": "RA",
|
| 181 |
"Benchmark": "GSM8K_deepseek_r1_denoising",
|
| 182 |
"WAR": 0.30,
|
|
|
|
| 184 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GSM8K/gsm8k_deepseek_r1_denoising)"
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"ID": 24,
|
| 188 |
"Category": "RA",
|
| 189 |
"Benchmark": "GSM8K_wac_gec",
|
| 190 |
"WAR": 1.97,
|
|
|
|
| 192 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/GSM8K/gsm8k_wac_gec)"
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"ID": 25,
|
| 196 |
+
"Category": "RA",
|
| 197 |
+
"Benchmark": "MMLU",
|
| 198 |
+
"WAR": 10.06,
|
| 199 |
+
"SED": 2.21,
|
| 200 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MMLU/mmlu)"
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"ID": 26,
|
| 204 |
"Category": "RA",
|
| 205 |
"Benchmark": "MMLU_deepseek_r1_denoising",
|
| 206 |
"WAR": 6.56,
|
|
|
|
| 208 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MMLU/mmlu_deepseek_r1_denoising)"
|
| 209 |
},
|
| 210 |
{
|
| 211 |
+
"ID": 27,
|
| 212 |
"Category": "RA",
|
| 213 |
"Benchmark": "MMLU_wac_gec",
|
| 214 |
"WAR": 2.98,
|
|
|
|
| 216 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MMLU/mmlu_wac_gec)"
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"ID": 28,
|
| 220 |
+
"Category": "ME",
|
| 221 |
+
"Benchmark": "MedMCQA",
|
| 222 |
+
"WAR": 6.31,
|
| 223 |
+
"SED": 6.18,
|
| 224 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedMCQA/medmcqa)"
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"ID": 29,
|
| 228 |
"Category": "ME",
|
| 229 |
"Benchmark": "MedMCQA_deepseek_r1_denoising",
|
| 230 |
"WAR": 3.44,
|
|
|
|
| 232 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedMCQA/medmcqa_deepseek_r1_denoising)"
|
| 233 |
},
|
| 234 |
{
|
| 235 |
+
"ID": 30,
|
| 236 |
"Category": "ME",
|
| 237 |
"Benchmark": "MedMCQA_wac_gec",
|
| 238 |
"WAR": 2.44,
|
|
|
|
| 240 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedMCQA/medmcqa_wac_gec)"
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"ID": 31,
|
| 244 |
+
"Category": "ME",
|
| 245 |
+
"Benchmark": "MedQA",
|
| 246 |
+
"WAR": 16.97,
|
| 247 |
+
"SED": 6.49,
|
| 248 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedQA/MedQA-USMLE-4-options)"
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"ID": 32,
|
| 252 |
"Category": "ME",
|
| 253 |
"Benchmark": "MedQA_deepseek_r1_denoising",
|
| 254 |
"WAR": 16.26,
|
|
|
|
| 256 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedQA/MedQA_deepseek_r1_denoising)"
|
| 257 |
},
|
| 258 |
{
|
| 259 |
+
"ID": 33,
|
| 260 |
"Category": "ME",
|
| 261 |
"Benchmark": "MedQA_wac_gec",
|
| 262 |
"WAR": 0.79,
|
|
|
|
| 264 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/MedQA/MedQA_wac_gec)"
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"ID": 34,
|
| 268 |
+
"Category": "SU",
|
| 269 |
+
"Benchmark": "Natural_questions",
|
| 270 |
+
"WAR": 0.17,
|
| 271 |
+
"SED": 2.90,
|
| 272 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Natural_questions/nq_open)"
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"ID": 35,
|
| 276 |
"Category": "SU",
|
| 277 |
"Benchmark": "Natural_questions_deepseek_r1_denoising",
|
| 278 |
"WAR": 0.06,
|
|
|
|
| 280 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Natural_questions/nq_open_deepseek_r1_denoising)"
|
| 281 |
},
|
| 282 |
{
|
| 283 |
+
"ID": 36,
|
| 284 |
"Category": "SU",
|
| 285 |
"Benchmark": "Natural_questions_wac_gec",
|
| 286 |
"WAR": 0.28,
|
|
|
|
| 288 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Natural_questions/nq_open_wac_gec)"
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"ID": 37,
|
| 292 |
+
"Category": "ME",
|
| 293 |
+
"Benchmark": "PubMedQA",
|
| 294 |
+
"WAR": 0.60,
|
| 295 |
+
"SED": 8.15,
|
| 296 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/PubMedQA/pubmed_qa)"
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"ID": 38,
|
| 300 |
"Category": "ME",
|
| 301 |
"Benchmark": "PubMedQA_deepseek_r1_denoising",
|
| 302 |
"WAR": 0.20,
|
|
|
|
| 304 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/PubMedQA/pubmed_qa_deepseek_r1_denoising)"
|
| 305 |
},
|
| 306 |
{
|
| 307 |
+
"ID": 39,
|
| 308 |
"Category": "ME",
|
| 309 |
"Benchmark": "PubMedQA_wac_gec",
|
| 310 |
"WAR": 0.00,
|
|
|
|
| 312 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/PubMedQA/pubmed_qa_wac_gec)"
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"ID": 40,
|
| 316 |
+
"Category": "TG",
|
| 317 |
+
"Benchmark": "Truthful_QA",
|
| 318 |
+
"WAR": 0.00,
|
| 319 |
+
"SED": 1.75,
|
| 320 |
+
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Truthful_QA/truthful_qa)"
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"ID": 41,
|
| 324 |
"Category": "TG",
|
| 325 |
"Benchmark": "Truthful_QA_deepseek_r1_denoising",
|
| 326 |
"WAR": 0.00,
|
|
|
|
| 328 |
"Download": "[下载](https://huggingface.co/datasets/lllouo/BD-benchmarks/tree/main/Truthful_QA/truthful_qa_deepseek_r1_denoising)"
|
| 329 |
},
|
| 330 |
{
|
| 331 |
+
"ID": 42,
|
| 332 |
"Category": "TG",
|
| 333 |
"Benchmark": "Truthful_QA_wac_gec",
|
| 334 |
"WAR": 0.00,
|