DeepSeek V3.2 Speciale Benchmark Details

DeepSeek V3.2 Speciale currently shows benchmark results led by AIME2025 (22 / 106, score 96), CodeForces (7 / 16, score 2701), HLE (74 / 159, score 30.60).

Benchmark Results

DeepSeek V3.2 Speciale

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

30.60

74 / 159

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

96

22 / 106

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

2701

7 / 16

Compare with other models