DeepSeek
deepseek-v3.2-exp
mit
Benchmark Average (0–100)
59.4%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
GPQA79.9%
Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.
AIME 202589.3%
AIME 2025 is a mathematics competition benchmark testing advanced problem-solving.
SWE-bench Verified67.8%
SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.
BrowseComp40.1%
BrowseComp tests web browsing comprehension, measuring ability to find and synthesize information from websites.
HLE19.8%
Humanity's Last Exam (HLE) is a multi-modal benchmark testing frontier knowledge across mathematics, humanities, and natural sciences with 2,500 expert-level questions.
OTHER BENCHMARKS
SimpleQA
97.1%
Terminal Bench
37.7%
MODEL INFO
Organization
DeepSeek
Context Window
163,840
Release Date
2025-09-29
Knowledge Cutoff
—
Parameters
685000000000.0B
License
mit
Input Price ($/M)
$0.2700
Output Price ($/M)
$0.4100
METADATA
Announcement Date
2025-09-29
Organization Country
CN
Canonical ID
—