AI Benchmark Model

DeepSeek V3.2 Exp (Non-reasoning)

Benchmark scores, pricing, speed, and model comparisons for DeepSeek V3.2 Exp (Non-reasoning).

Key scores

Intelligence28.4Index score
Coding30.0Index score
Math57.7Index score
Blended Cost$0.31Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

10 tracked benchmark rows for DeepSeek V3.2 Exp (Non-reasoning).

MMLU Pro Knowledge
83.6%
GPQA Reasoning
73.8%
AIME 2025 Math
57.7%
LiveCodeBench Code
55.4%
IFBench Other
43.1%
LCR Other
43.0%
SciCode Other
39.9%
TAU2 Other
33.9%
TerminalBench Hard Other
25.0%
HLE Other
8.6%

Comments (0)

No comments yet

Be the first to share your thoughts!