tw-exam-bench
An academic knowledge evaluation benchmark composed of questions from Taiwan national examinations. It covers multiple disciplines in a four-option single-choice format, with data sourced from open data published by the Ministry of Examination.
Timeline (last 90 days)
OpenTWBench is an open evaluation suite built around two benchmarks: tw-exam-bench and tw-formosa-bench.
The tw-exam-bench data comes from fifteen years of national examination questions released as open data by Taiwan's Ministry of Examination, covering 148 subjects with a total of 255,854 four-choice multiple-choice questions.
In tw-exam-bench, the answer-key consistency rate for 31,312 groups of duplicated questions reached 99.91%, and the only 27 discrepancies were verified and attributed one by one.
In tw-exam-bench, manual review removed 2,180 questions whose stems depend on images but whose text does not carry the images, and all final scores are calculated based on the remaining 253,674 questions.
All Facts (4)
OpenTWBench is an open evaluation suite built around two benchmarks: tw-exam-bench and tw-formosa-bench.
50%UnverifiedThe tw-exam-bench data comes from fifteen years of national examination questions released as open data by Taiwan's Ministry of Examination, covering 148 subjects with a total of 255,854 four-choice multiple-choice questions.
50%UnverifiedIn tw-exam-bench, the answer-key consistency rate for 31,312 groups of duplicated questions reached 99.91%, and the only 27 discrepancies were verified and attributed one by one.
50%UnverifiedIn tw-exam-bench, manual review removed 2,180 questions whose stems depend on images but whose text does not carry the images, and all final scores are calculated based on the remaining 253,674 questions.
50%