DeepSeek V3.2 Speciale
Released · 63 days after DeepSeek V3.2 Exp
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Global rank#224 of 597 LLMs
TierEfficient
Intelligence Index22.6
Math Index96.7
Reasoning & knowledge
MMLU-Pro
86%
GPQA Diamond
87%
Humanity's Last Exam
29%
Long-context reasoning
64%
Coding
LiveCodeBench
90%
SciCode
44%
Agentic & tool use
Terminal-Bench Hard
35%
τ²-Bench Telecom
0%
Math & instruction following
AIME 2025
97%
IFBench
64%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — DeepSeek V3.2 Speciale isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →