OpenAI
o3-2025-04-16
proprietaryMultimodal
Benchmark Average (0–100)
63.3%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
GPQA83.3%
Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.
AIME 202586.4%
AIME 2025 is a mathematics competition benchmark testing advanced problem-solving.
SWE-bench Verified69.1%
SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.
BrowseComp49.7%
BrowseComp tests web browsing comprehension, measuring ability to find and synthesize information from websites.
HLE14.7%
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.
MMMU-Pro76.4%
MMMU-Pro is a more challenging version of MMMU with harder multimodal understanding tasks.
OTHER BENCHMARKS
MMMU
82.9%
ARC-AGI v2
6.5%
CharXIV-R
78.6%
FrontierMath
15.8%
MODEL INFO
Organization
OpenAI
Context Window
200,000
Release Date
2025-04-16
Knowledge Cutoff
2024-05-31
Parameters
—
License
proprietary
Input Price ($/M)
$2.0000
Output Price ($/M)
$8.0000
METADATA
Announcement Date
2025-04-16
Organization Country
US
Canonical ID
—