Reasoning Benchmark Suite
Benchmarks
TaskDatasetSOTA resultTrendResults
Reasoning Benchmark Suite Aggregate
59.44Average Score
36
Reasoning Benchmark Suite (GSM8K, MATH500, GPQA, CSQA, AQuA, MMLU)
86.61Average Accuracy
7
Reasoning Benchmark Suite (MATH500, GSM8K, AMC23, Minerva, MMLU, MMLU-Pro, GPQA)
81.15MATH500 Score
2
Reasoning Benchmark Suite Aggregate
-1.5ASG
1