AI Model Release Tracker

Gemini 3.7 Flash

Released

Gemini 3.7 Flash is an AI model released by Google on Thursday, Aug 13 2026, 23 days after Gemini 3.5 Flash Cyber. It has a 1M token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover MRCR v2 (8-needle), BullshitBench v2, ProgramBench, DeepSWE 1.1, FrontierCode v1.1 (Main), Terminal-Bench 4.0, and 17 more.

Available from

Google AI Studio—flex$0.375$1.8751M
Google AI Studio——$0.75$3.751M
Googleglobal—$0.75$3.751M
Googleus—$0.825$4.1251M
Google AI Studio—priority$1.35$6.751M
Googleglobalpriority$1.35$6.751M
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Checked October 19, 2026Third-party rates from openrouter.ai, not the lab’s own list price.

Benchmarks

Coding

ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better.via ProgramBench
0%
#11 of 25
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better.
65.3%
#25 of 42
FrontierCode v1.1 (Main)Agentic coding — A set of very hard, frontier-difficulty coding tasks an AI agent has to complete end to end. The score is the share of tasks in the main split it solves. Higher is better.
43.6%main split
#9 of 11

Terminal & CLI

Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better.via Terminal-Bench
11.21%
#35 of 36
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set)
14.9%
#6 of 8
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better.
85.8%
#12 of 40

Agentic & tool use

OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better.
38.1%
#11 of 12
Agent's Last ExamAgentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better.
26.3%pass@1
#11 of 15
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better.
30.4%
#21 of 32

Reasoning & science

Humanity's Last Exam (Verified)Multidisciplinary reasoning — The re-checked edition of Humanity's Last Exam: the same extremely hard expert questions, minus the ones found to be flawed or wrongly answered. Scores on it run lower than on the original exam, so read the two as separate tests rather than a before-and-after. Higher is better.
53.6%
#2 of 3
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better.via BenchLM
84.6%
#11 of 41
BioMysteryBenchBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better.
43.5%hard
87.1%human solved
hard
#7 of 10
human solved
#7 of 10
LAB-Bench 2Biology — Everyday tasks from a working biology lab — reading protocols, interpreting figures and sequence data, and answering the practical questions a researcher hits at the bench. Higher is better.
82.1%
#3 of 4

Knowledge work

AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals
56
#3 of 7
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo)
1525
#15 of 25

Finance

Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better.
59%
#4 of 13

Multimodal

CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better.
84.5%
88.7%with tools
#10 of 28
with tools
#8 of 19
GDP.PDFDocument comprehension — Real professional PDFs — filings, reports, technical documents — with questions an expert in that field would ask. Tests whether the AI reads the page as a document, layout and figures included, rather than as loose text. Higher is better.
34%
#3 of 10
LVBenchVideo understanding — Can the AI follow a very long video — up to an hour — and answer questions that need details from far apart in it? Higher is better.
85.4%
#3 of 5

Long context

MRCR v2 (8-needle)Long context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better.
97%128k average
62.5%1M pointwise
128k average
#1
1M pointwise
#1

Robustness

BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better.via BullshitBench
35%
#57 of 100

Community preference

threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.via threejseval
1468
#15 of 29

Source: BenchLM, retrieved 28 September 2026 · Source: ProgramBench, retrieved 11 September 2026 · Source: Terminal-Bench, retrieved 5 September 2026. Other sources are identified on the linked benchmark pages.

Compare Gemini 3.7 Flash with

Gemini 3.7 Flash

Suggested comparisons

Gemini 3.7 FlashvsGemini 4 CarbonGemini 3.7 FlashvsGPT-6.1 TerraGemini 3.7 FlashvsClaude Fable 5.2Gemini 3.7 FlashvsMuse EmberGemini 3.7 FlashvsGrok 4.7Gemini 3.7 FlashvsDeepSeek-V4.1-Flash-1017Gemini 3.7 FlashvsMistral Large 4Gemini 3.7 FlashvsKimi K3.1 ProGemini 3.7 FlashvsGLM-5.3-FlashGemini 3.7 FlashvsQwen4-Max PreviewGemini 3.7 FlashvsNemotron 3.5 Bolt E4B 4GB

About

Gemini 3.7 Flash was released on August 13, 2026 as an update for coding agents and knowledge work. Google reported 65.3% on DeepSWE v1.1 at launch, compared with 49.0% for 3.6 Flash in its evaluation of long-horizon software engineering.

The model supported multimodal inputs and a one-million-token context, with access across Google's developer tools and enterprise products. Google also highlighted document comprehension and automated workflows, extending the model's target tasks beyond writing and repairing code.

Frequently asked questions

Gemini 3.7 Flash was released by Google on Thursday, Aug 13 2026.

All Google releases

33 tracked