GSM8K
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GSM8K
92.6Accuracy
23
GSM8K
98Accuracy (GSM8K)
22
GSM8K
94.01GSM8K Math Score
22
GSM8k (test)
70.2PR-AUC
22
GSM8K
89.92GSM8K Accuracy
22
GSM8K
0.952Accuracy
22
GSM8k
91.7Accuracy
22
GSM8K (train)
89.8Accuracy
22
GSM8K
94.91Pass@1
22
GSM8K
96.3Accuracy
21
GSM8K
93.9Accuracy (mean@4)
21
GSM8K
1.02Utility Ratio (UR)
21
GSM8K
90.28Pass@1
21
GSM8k
78.09Accuracy
21
gsm8k cot
99.49Accuracy
21
GSM8K Qwen2.5-Instruct (test)
93.7Accuracy
21
GSM8K
97.1p_T Score
21
GSM8K
41.93Performance
21
GSM8K subset of 100 questions (test)
87Accuracy
21
GSM8K
94.92Accuracy
21
GSM8k
90.58Pass@1
21
GSM8K
93.1Accuracy @ 128 Tokens
21
GSM8K
56.79GSM8K Accuracy
21
GSM8K (test)
92.4Accuracy
20
GSM8K
90.82Pass@1
20