gemini-2.5-pro-preview-06-05
proprietaryMultimodal
Benchmark Average (0–100)
65.8%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
GPQA86.4%
Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.
AIME 202588.0%
AIME 2025 is a mathematics competition benchmark testing advanced problem-solving.
SWE-bench Verified67.2%
SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.
HLE21.6%
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
MMMU
82.0%
SimpleQA
54.0%
MODEL INFO
Organization
Google
Context Window
1,048,576
Release Date
2025-06-05
Knowledge Cutoff
2025-01-31
Parameters
—
License
proprietary
Input Price ($/M)
$1.2500
Output Price ($/M)
$10.0000
METADATA
Announcement Date
2025-06-05
Organization Country
US
Canonical ID
—