Google

gemini-3.1-pro-preview

proprietaryMultimodal
Benchmark Average (0–100)
80.9%
Average of non-null benchmark scores across all evaluated tasks.

BENCHMARK SCORES

GPQA94.3%

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

SWE-bench Verified80.6%

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

MMMLU92.6%

Multilingual MMLU tests knowledge across many languages and subject areas.

BrowseComp85.9%

BrowseComp tests web browsing comprehension, measuring ability to find and synthesize information from websites.

HLE51.4%

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-Pro80.5%

MMMU-Pro is a more challenging version of MMMU with harder multimodal understanding tasks.

OTHER BENCHMARKS

ARC-AGI v2
77.1%
MCP Atlas
69.2%

MODEL INFO

Organization
Google
Context Window
1,048,576
Release Date
2026-02-19
Knowledge Cutoff
2025-01-31
Parameters
License
proprietary
Input Price ($/M)
$2.5000
Output Price ($/M)
$15.0000

METADATA

Announcement Date
2026-02-19
Organization Country
US
Canonical ID