← All benchmarks

DeepSeek V3.2 (Reasoning)

DeepSeek · Released 2025-12-01 · Independent benchmark scores from Artificial Analysis

Intelligence Index
32.0
Output speed
0.0
tokens/sec
Blended price
$0.32
per 1M tokens
Time to first token
0.00s

Model metadata

Model IDd621247c-d47e-458c-82cb-a166bc3b37e5
Slugdeepseek-v3-2-reasoning
Release date2025-12-01
ProviderDeepSeek
Provider slugdeepseek
Output speed0.0 tok/s
Time to first token0.00s
Time to first answer0.00s
Blended price ($/1M)$0.32
Input price ($/1M)$0.28
Output price ($/1M)$0.42

All evaluation scores (17)

aime
aime 2592.0%
artificial analysis coding index44.20
artificial analysis intelligence index32.00
artificial analysis math index92.00
gpqa84.0%
hle22.2%
ifbench60.7%
lcr65.0%
livecodebench86.2%
math 500
mmlu pro86.2%
scicode38.9%
tau banking18.8%
tau290.6%
terminalbench hard35.6%
terminalbench v2 146.8%

Source: artificialanalysis.ai/models/deepseek-v3-2-reasoning

Benchmark data from Artificial Analysis.