Gemini 3.5 Flash
Google · 3 thinking configurations
Intelligence32.6
Input / 1M$1.50
Output / 1M$9.00
Context1M
Tariff: Google · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 2 without both values
Selected: thinking high · Click a point to switch configuration
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...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
32.6 pointsDeepSWE · pass@1Software-engineering tasks on mini-swe-agent v1.1. Pass@1 across evaluated runs, with measured cost per task. The 95% intervals may overlap.
36.1 % ±4.0GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
92.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
42.7 %SciCodeCode generation for scientific research problems.
53.9 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
78.7 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
95.3 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
76.3 %MMMU-ProMultimodal understanding of academic problems that include images.
84.3 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
51.4 %Specifications from the catalog
Inputtext, image, video, file, audio
Outputtext
Tool callingYes
Structured outputYes
Speed191.5 tok/s
First token17.40 s
Maximum output65.5K
Catalog listing date2026-05-19
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $3.45 / task · 105 mean steps · 75.7K mean output tokens. Published by the source 9/22/2026.