gemini-3.5-flash
proprietaryMultimodal
Benchmark Average (0–100)
61.9%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
HLE40.2%
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-Pro83.6%
MMMU-Pro is a more challenging version of MMMU with harder multimodal understanding tasks.
OTHER BENCHMARKS
ToolAthalon
56.5%
ARC-AGI v2
72.1%
CharXIV-R
84.2%
MCP Atlas
83.6%
MODEL INFO
Organization
Google
Context Window
1,048,576
Release Date
2026-05-19
Knowledge Cutoff
2026-01-31
Parameters
—
License
proprietary
Input Price ($/M)
$1.5000
Output Price ($/M)
$9.0000
METADATA
Announcement Date
2026-05-19
Organization Country
US
Canonical ID
—