simpleqa

v1.0

SimpleQA: 4,326 short, fact-seeking questions from OpenAI for evaluating language model factuality. Uses LLM-as-a-judge grading. Source: https://openai.com/index/introducing-simpleqa/

uvx harbor run -d simpleqa@1.0

Tasks (4326)

simpleqa-1899
uvx harbor run -d simpleqa@1.0 -t simpleqa-1899
b8f0fa9
simpleqa-19
uvx harbor run -d simpleqa@1.0 -t simpleqa-19
b8f0fa9
simpleqa-190
uvx harbor run -d simpleqa@1.0 -t simpleqa-190
b8f0fa9
simpleqa-1900
uvx harbor run -d simpleqa@1.0 -t simpleqa-1900
b8f0fa9
simpleqa-1901
uvx harbor run -d simpleqa@1.0 -t simpleqa-1901
b8f0fa9
simpleqa-1902
uvx harbor run -d simpleqa@1.0 -t simpleqa-1902
b8f0fa9
simpleqa-1903
uvx harbor run -d simpleqa@1.0 -t simpleqa-1903
b8f0fa9
simpleqa-1904
uvx harbor run -d simpleqa@1.0 -t simpleqa-1904
b8f0fa9
simpleqa-1905
uvx harbor run -d simpleqa@1.0 -t simpleqa-1905
b8f0fa9
simpleqa-1906
uvx harbor run -d simpleqa@1.0 -t simpleqa-1906
b8f0fa9
simpleqa-1907
uvx harbor run -d simpleqa@1.0 -t simpleqa-1907
b8f0fa9
simpleqa-1908
uvx harbor run -d simpleqa@1.0 -t simpleqa-1908
b8f0fa9
simpleqa-1909
uvx harbor run -d simpleqa@1.0 -t simpleqa-1909
b8f0fa9
simpleqa-191
uvx harbor run -d simpleqa@1.0 -t simpleqa-191
b8f0fa9
simpleqa-1910
uvx harbor run -d simpleqa@1.0 -t simpleqa-1910
b8f0fa9
simpleqa-1911
uvx harbor run -d simpleqa@1.0 -t simpleqa-1911
b8f0fa9
simpleqa-1912
uvx harbor run -d simpleqa@1.0 -t simpleqa-1912
b8f0fa9
simpleqa-1913
uvx harbor run -d simpleqa@1.0 -t simpleqa-1913
b8f0fa9
simpleqa-1914
uvx harbor run -d simpleqa@1.0 -t simpleqa-1914
b8f0fa9
simpleqa-1915
uvx harbor run -d simpleqa@1.0 -t simpleqa-1915
b8f0fa9
simpleqa-1916
uvx harbor run -d simpleqa@1.0 -t simpleqa-1916
b8f0fa9
simpleqa-1917
uvx harbor run -d simpleqa@1.0 -t simpleqa-1917
b8f0fa9
simpleqa-1918
uvx harbor run -d simpleqa@1.0 -t simpleqa-1918
b8f0fa9
simpleqa-1919
uvx harbor run -d simpleqa@1.0 -t simpleqa-1919
b8f0fa9
simpleqa-192
uvx harbor run -d simpleqa@1.0 -t simpleqa-192
b8f0fa9
simpleqa-1920
uvx harbor run -d simpleqa@1.0 -t simpleqa-1920
b8f0fa9
simpleqa-1921
uvx harbor run -d simpleqa@1.0 -t simpleqa-1921
b8f0fa9
simpleqa-1922
uvx harbor run -d simpleqa@1.0 -t simpleqa-1922
b8f0fa9
simpleqa-1923
uvx harbor run -d simpleqa@1.0 -t simpleqa-1923
b8f0fa9
simpleqa-1924
uvx harbor run -d simpleqa@1.0 -t simpleqa-1924
b8f0fa9
simpleqa-1925
uvx harbor run -d simpleqa@1.0 -t simpleqa-1925
b8f0fa9
simpleqa-1926
uvx harbor run -d simpleqa@1.0 -t simpleqa-1926
b8f0fa9
simpleqa-1927
uvx harbor run -d simpleqa@1.0 -t simpleqa-1927
b8f0fa9
simpleqa-1928
uvx harbor run -d simpleqa@1.0 -t simpleqa-1928
b8f0fa9
simpleqa-1929
uvx harbor run -d simpleqa@1.0 -t simpleqa-1929
b8f0fa9
simpleqa-193
uvx harbor run -d simpleqa@1.0 -t simpleqa-193
b8f0fa9
simpleqa-1930
uvx harbor run -d simpleqa@1.0 -t simpleqa-1930
b8f0fa9
simpleqa-1931
uvx harbor run -d simpleqa@1.0 -t simpleqa-1931
b8f0fa9
simpleqa-1932
uvx harbor run -d simpleqa@1.0 -t simpleqa-1932
b8f0fa9
simpleqa-1933
uvx harbor run -d simpleqa@1.0 -t simpleqa-1933
b8f0fa9
simpleqa-1934
uvx harbor run -d simpleqa@1.0 -t simpleqa-1934
b8f0fa9
simpleqa-1935
uvx harbor run -d simpleqa@1.0 -t simpleqa-1935
b8f0fa9
simpleqa-1936
uvx harbor run -d simpleqa@1.0 -t simpleqa-1936
b8f0fa9
simpleqa-1937
uvx harbor run -d simpleqa@1.0 -t simpleqa-1937
b8f0fa9
simpleqa-1938
uvx harbor run -d simpleqa@1.0 -t simpleqa-1938
b8f0fa9
simpleqa-1939
uvx harbor run -d simpleqa@1.0 -t simpleqa-1939
b8f0fa9
simpleqa-194
uvx harbor run -d simpleqa@1.0 -t simpleqa-194
b8f0fa9
simpleqa-1940
uvx harbor run -d simpleqa@1.0 -t simpleqa-1940
b8f0fa9
simpleqa-1941
uvx harbor run -d simpleqa@1.0 -t simpleqa-1941
b8f0fa9
simpleqa-1942
uvx harbor run -d simpleqa@1.0 -t simpleqa-1942
b8f0fa9
simpleqa-1943
uvx harbor run -d simpleqa@1.0 -t simpleqa-1943
b8f0fa9
simpleqa-1944
uvx harbor run -d simpleqa@1.0 -t simpleqa-1944
b8f0fa9
simpleqa-1945
uvx harbor run -d simpleqa@1.0 -t simpleqa-1945
b8f0fa9
simpleqa-1946
uvx harbor run -d simpleqa@1.0 -t simpleqa-1946
b8f0fa9
simpleqa-1947
uvx harbor run -d simpleqa@1.0 -t simpleqa-1947
b8f0fa9
simpleqa-1948
uvx harbor run -d simpleqa@1.0 -t simpleqa-1948
b8f0fa9
simpleqa-1949
uvx harbor run -d simpleqa@1.0 -t simpleqa-1949
b8f0fa9
simpleqa-195
uvx harbor run -d simpleqa@1.0 -t simpleqa-195
b8f0fa9
simpleqa-1950
uvx harbor run -d simpleqa@1.0 -t simpleqa-1950
b8f0fa9
simpleqa-1951
uvx harbor run -d simpleqa@1.0 -t simpleqa-1951
b8f0fa9
simpleqa-1952
uvx harbor run -d simpleqa@1.0 -t simpleqa-1952
b8f0fa9
simpleqa-1953
uvx harbor run -d simpleqa@1.0 -t simpleqa-1953
b8f0fa9
simpleqa-1954
uvx harbor run -d simpleqa@1.0 -t simpleqa-1954
b8f0fa9
simpleqa-1955
uvx harbor run -d simpleqa@1.0 -t simpleqa-1955
b8f0fa9
simpleqa-1956
uvx harbor run -d simpleqa@1.0 -t simpleqa-1956
b8f0fa9
simpleqa-1957
uvx harbor run -d simpleqa@1.0 -t simpleqa-1957
b8f0fa9
simpleqa-1958
uvx harbor run -d simpleqa@1.0 -t simpleqa-1958
b8f0fa9
simpleqa-1959
uvx harbor run -d simpleqa@1.0 -t simpleqa-1959
b8f0fa9
simpleqa-196
uvx harbor run -d simpleqa@1.0 -t simpleqa-196
b8f0fa9
simpleqa-1960
uvx harbor run -d simpleqa@1.0 -t simpleqa-1960
b8f0fa9
simpleqa-1961
uvx harbor run -d simpleqa@1.0 -t simpleqa-1961
b8f0fa9
simpleqa-1962
uvx harbor run -d simpleqa@1.0 -t simpleqa-1962
b8f0fa9
simpleqa-1963
uvx harbor run -d simpleqa@1.0 -t simpleqa-1963
b8f0fa9
simpleqa-1964
uvx harbor run -d simpleqa@1.0 -t simpleqa-1964
b8f0fa9
simpleqa-1965
uvx harbor run -d simpleqa@1.0 -t simpleqa-1965
b8f0fa9
simpleqa-1966
uvx harbor run -d simpleqa@1.0 -t simpleqa-1966
b8f0fa9
simpleqa-1967
uvx harbor run -d simpleqa@1.0 -t simpleqa-1967
b8f0fa9
simpleqa-1968
uvx harbor run -d simpleqa@1.0 -t simpleqa-1968
b8f0fa9
simpleqa-1969
uvx harbor run -d simpleqa@1.0 -t simpleqa-1969
b8f0fa9
simpleqa-197
uvx harbor run -d simpleqa@1.0 -t simpleqa-197
b8f0fa9
simpleqa-1970
uvx harbor run -d simpleqa@1.0 -t simpleqa-1970
b8f0fa9
simpleqa-1971
uvx harbor run -d simpleqa@1.0 -t simpleqa-1971
b8f0fa9
simpleqa-1972
uvx harbor run -d simpleqa@1.0 -t simpleqa-1972
b8f0fa9
simpleqa-1973
uvx harbor run -d simpleqa@1.0 -t simpleqa-1973
b8f0fa9
simpleqa-1974
uvx harbor run -d simpleqa@1.0 -t simpleqa-1974
b8f0fa9
simpleqa-1975
uvx harbor run -d simpleqa@1.0 -t simpleqa-1975
b8f0fa9
simpleqa-1976
uvx harbor run -d simpleqa@1.0 -t simpleqa-1976
b8f0fa9
simpleqa-1977
uvx harbor run -d simpleqa@1.0 -t simpleqa-1977
b8f0fa9
simpleqa-1978
uvx harbor run -d simpleqa@1.0 -t simpleqa-1978
b8f0fa9
simpleqa-1979
uvx harbor run -d simpleqa@1.0 -t simpleqa-1979
b8f0fa9
simpleqa-198
uvx harbor run -d simpleqa@1.0 -t simpleqa-198
b8f0fa9
simpleqa-1980
uvx harbor run -d simpleqa@1.0 -t simpleqa-1980
b8f0fa9
simpleqa-1981
uvx harbor run -d simpleqa@1.0 -t simpleqa-1981
b8f0fa9
simpleqa-1982
uvx harbor run -d simpleqa@1.0 -t simpleqa-1982
b8f0fa9
simpleqa-1983
uvx harbor run -d simpleqa@1.0 -t simpleqa-1983
b8f0fa9
simpleqa-1984
uvx harbor run -d simpleqa@1.0 -t simpleqa-1984
b8f0fa9
simpleqa-1985
uvx harbor run -d simpleqa@1.0 -t simpleqa-1985
b8f0fa9
simpleqa-1986
uvx harbor run -d simpleqa@1.0 -t simpleqa-1986
b8f0fa9
simpleqa-1987
uvx harbor run -d simpleqa@1.0 -t simpleqa-1987
b8f0fa9
simpleqa-1988
uvx harbor run -d simpleqa@1.0 -t simpleqa-1988
b8f0fa9