DataLearner logo

PaLM-Coder Benchmark Details

PaLM-Coder currently shows benchmark results led by HumanEval pass@100 (10 / 21, score 88.40), HumanEval (68 / 101, score 35.90), MBPP (50 / 70, score 47).

Benchmark Results

PaLM-Coder

Benchmark Results

Thinking

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
47
50 / 70
HumanEval
Standard Mode
35.90
68 / 101

Other

1 evaluations
Benchmark / mode
Score
Rank/total
HumanEval pass@100
Standard Mode
88.40
10 / 21
Compare with other models