Pythia Benchmark Details

Pythia currently shows benchmark results led by AGIEval (25 / 28, score 25.30), C-Eval (44 / 48, score 26.20), MMLU (123 / 124, score 25.10).

Benchmark Results

Pythia

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

26.20

44 / 48

Standard Mode

25.10

123 / 124

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

25.30

25 / 28

Compare with other models