Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SciBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Scientific ReasoningSciBench
Accuracy44.3
33
ChemistrySciBench
Accuracy66.4
32
ScienceSciBench
Accuracy (SciBench)28.3
24
Physics problem solvingScibench fund
Accuracy74.6
24
Scientific Problem SolvingSciBench-107
Atkins Score62.5
24
Scientific ReasoningSciBench Physics
Accuracy82.4
20
Scientific ReasoningSciBench Chemistry
Accuracy73.2
20
General and STEM reasoningSciBench
Pass@171.39
20
Uncertainty CalibrationSciBench
AUROC78.7
18
Scientific Problem SolvingSciBench
Pass@2077.46
17
Scientific ReasoningSciBench
pass@344.36
14
College-level Science Problem SolvingSciBench
Accuracy72.1
12
Scientific Problem SolvingSciBench
Accuracy4
12
Scientific ReasoningSciBench
Pass@129.64
12
Scientific ReasoningSciBench
Accuracy7.4
10
Scientific ReasoningSCIBENCH (test)
Accuracy70.8
6
Scientific Problem SolvingSciBench
Diff Accuracy65.47
6
Scientific ReasoningSciBench
Pass@1072.23
6
ScienceSciBench chemistry
Score90.61
3
Showing 19 of 19 rows