Creator
DeepSeek
Released
2026-04-24
Intelligence
51.5
Artificial Analysis Index
Coding
47.5
Artificial Analysis Index
In $/1M
$0.43
input tokens
Out $/1M
$0.87
output tokens
Blended $/1M
$0.54
3:1 blended
Speed
60
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
89
Humanity’s Last Exam
36
MMLU-Pro—
SciCode
50
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
96
Terminal-Bench Hard
46
IFBench
76