Creator
DeepSeek
Released
2026-04-24
Intelligence
46.5
Artificial Analysis Index
Coding
38.7
Artificial Analysis Index
In $/1M
$0.14
input tokens
Out $/1M
$0.28
output tokens
Blended $/1M
$0.17
3:1 blended
Speed
116
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
89
Humanity’s Last Exam
32
MMLU-Pro—
SciCode
45
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
95
Terminal-Bench Hard
36
IFBench
79