AI Hub
← All models

DeepSeek V3.2 Speciale vs Hermes 4 - Llama-3.1 405B

DeepSeek vs Nous Research — benchmarks, pricing, and capabilities side by side.

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 73.5)
  • DeepSeek V3.2 Speciale is cheaper ($0.29 vs $1.00 per 1M input)
DeepSeek V3.2 SpecialeHermes 4 - Llama-3.1 405B
Intelligence index89.973.5
DeveloperDeepSeekNous Research
TypeLLMLLM
AccessOpen weights
Context window163,840 tokens
Input price$0.29 / 1M$1.00 / 1M
Output price$0.43 / 1M$3.00 / 1M
Speed34 tok/s
ReleasedDecember 1, 2025August 27, 2025
Parameters
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek V3.2 Speciale
Hermes 4 - Llama-3.1 405B
AIME 2025
96.7
69.7
GPQA Diamond
87.1
72.7
Humanity’s Last Exam
26.1
10.3
LiveCodeBench
89.6
68.6
MMLU-Pro
86.3
82.9