Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Game of 24

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningGame of 24
Accuracy98.3
62
Mathematical ReasoningGame of 24 (test)
Accuracy98
35
Arithmetic reasoning (multi-solution)Game of 24 4nu 137 (test)
Multi Solution Accuracy76.25
12
Arithmetic ReasoningGame of 24 95 (test)
Success Rate100
9
Game of 24Game of 24 100 tasks GPT-4
Success Rate74
8
Mathematical ReasoningGame of 24
pass@10.84
6
Mathematical ReasoningGame of 24
pass@1100
4
Arithmetic ReasoningGame of 24
Metric-
0
Showing 8 of 8 rows