Thinking-enabled DeepSeek-V3.1-Terminus with improved language consistency, upgraded Code/Search Agents, and stronger stability and reliability versus V3.1. FP8.
Context Window
128.0K
Max Output
65.5K
Input Price (Auto)
$0.26/1M
Output Price (Auto)
$0.73/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
33.9
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
33.7
Agentic Index
28.6
GPQA Diamond
Graduate-level scientific reasoning
79.2%
Better than 81% of models compared
HLE
Humanity's Last Exam
15.2%
Better than 84% of models compared
IFBench
Instruction-following benchmark
57.0%
Better than 76% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
37.1%
Better than 53% of models compared
AA-LCR
Long context reasoning evaluation
65.0%
Better than 88% of models compared
GDPval-AA
Economically valuable tasks
23.8%
Better than 80% of models compared
CritPt
Research-level physics reasoning
0.0%
Better than 36% of models compared
SciCode
Python programming for scientific computing
40.6%
Better than 85% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
30.3%
Better than 79% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
89.7%
Better than 90% of models compared
MMLU-Pro
Professional and academic subject knowledge
85.1%
Better than 91% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
23.4%
Better than 79% of models compared
Last updated May 15, 2026
Artificial AnalysisLiveCodeBench
Contamination-free coding benchmark
79.8%
Better than 92% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
85.3%
Better than 38% of models compared
