all the models — AI benchmark observatory
← Models

DeepSeek-V3.2 (Thinking)

DeepSeek · open weight · deepseek-reasoner

DeepSeek-V3.2 in thinking mode. A powerful reasoning model with 685B parameters using DeepSeek Sparse Attention (DSA). This mode enables extended chain-of-thought reasoning for complex problem-solving tasks. Supports JSON output and tool calls.

AIME 2025HMMT 2025MMLU-ProLiveCodeBencGPQAt2-bench

Benchmark scores

BenchmarkScore
AIME 20250.93
HMMT 20250.90
MMLU-Pro0.85
LiveCodeBench0.83
GPQA0.82
t2-bench0.80
SWE-Bench Verified0.73
Humanity's Last Exam0.25

Pricing

  • No provider pricing.

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.