GSM8K
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GSM8K
5.83Inference Cost (USD)
2
GSM8K
0.056MAE
2
GSM8K (test)
2.23Speedup
2
GSM8K
55.65Accuracy
2
GSM8K
93.83pass@4 Accuracy
2
GSM8K
91.6Accuracy
2
GSM8K
4.73Avg Length
2
GSM8K Multi
64.3Accuracy
2
GSM8K
0.423Scalar Regret
1
GSM8K Multi-step
54CR (%)
1
GSM8K Arithmetic
59Completion Rate
1
GSM8K
28.3Error Rate (%)
1
GSM8K
11.1AUROC
1
GSM8K lm-eval-harness 0.4.11
94.41GSM8K Flexible Extraction Accuracy
1
GSM8K (test)
0Accuracy
1
GSM8K Hard (100-item)
87.7Baseline Accuracy
1
GSM8K
78.8Base Accuracy
1
GSM8K (main)
73.7Monotonicity Rate
1
GSM8K VeRA-E
94.85Accuracy (Avg@5, Seeds)
1
GSM8K
39.4GSM8K Score
1
GSM8K
0.94Accuracy
1
GSM8K
—Primary metric
0
GSM8K
—Primary metric
0
GSM8K (test)
—Primary metric
0