DeepSeek-V2-236B-Chat Benchmark Details

DeepSeek-V2-236B-Chat currently shows benchmark results led by MMLU Pro (133 / 176, score 54.81), Aider-Polyglot (52 / 59, score 17.80).

Benchmark Results

DeepSeek-V2-236B-Chat

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

unknown

54.81

133 / 176

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

17.80

52 / 59

Compare with other models