Google

Gemini 3.5 Flash

by Googletext+image+file+audio+video->text7 endpoints
Neura Intelligence Index
54.4/ 100
Rank
#165
Confidence
high
Benchmarks
8(21% coverage)

Overview

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

Capabilities

Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
TextImageVideoFileAudio
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
65.5K tokens
Knowledge Cutoff
2025-01-01
Tokenizer
Gemini
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
May 19, 20264mo

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Benchmark Performance

general

BenchmarkScoreSource
MRCR v2
26.6
verified

coding

BenchmarkScoreSource
SWE-Bench Pro
55.1
verified

reasoning

BenchmarkScoreSource
ARC-AGI v2
72.1
verified
Humanity's Last Exam
40.2
verified

multimodal

BenchmarkScoreSource
CharXiv Reasoning
84.2
verified
MMMU-Pro
83.6
verified

agent

BenchmarkScoreSource
MCP Atlas
83.6
verified
Toolathlon
56.5
verified

Performance Over Time

Pricing

Per 1M tokens
Input$1.50
Output$9.00
Cache read$0.15
Cache write$0.08
Audio$3.00
Reasoning$9.00
Image$1.50
Added
May 19, 2026
Last synced 9/19/2026