AI Hub
← All models

Apriel-v1.6-15B-Thinker vs DeepSeek V3.2 Speciale

ServiceNow vs DeepSeek — benchmarks, pricing, and capabilities side by side.

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 80.3)
  • Apriel-v1.6-15B-Thinker is cheaper ($0.00 vs $0.29 per 1M input)
Apriel-v1.6-15B-ThinkerDeepSeek V3.2 Speciale
Intelligence index80.389.9
DeveloperServiceNowDeepSeek
TypeLLMLLM
AccessOpen weights
Context window163,840 tokens
Input price$0.00 / 1M$0.29 / 1M
Output price$0.00 / 1M$0.43 / 1M
Speed
ReleasedNovember 25, 2025December 1, 2025
Parameters
Input modalitiesText
Output modalitiesText

Shared benchmarks

Apriel-v1.6-15B-Thinker
DeepSeek V3.2 Speciale
AIME 2025
88
96.7
GPQA Diamond
73.3
87.1
Humanity’s Last Exam
9.8
26.1
LiveCodeBench
80.7
89.6
MMLU-Pro
79
86.3