Google

gemini-2.5-flash

proprietaryMultimodal
Benchmark Average (0–100)
56.6%
Average of non-null benchmark scores across all evaluated tasks.

BENCHMARK SCORES

GPQA82.8%

Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.

AIME 202572.0%

AIME 2025 is a mathematics competition benchmark testing advanced problem-solving.

SWE-bench Verified60.4%

SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.

HLE11.0%

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
79.7%
SimpleQA
26.9%

MODEL INFO

Organization
Google
Context Window
1,048,576
Release Date
2025-05-20
Knowledge Cutoff
2025-01-31
Parameters
License
proprietary
Input Price ($/M)
$0.3000
Output Price ($/M)
$2.5000

METADATA

Announcement Date
2025-05-20
Organization Country
US
Canonical ID