BenchLeader

Gemini 3.6 Flash vs Gemini 3.7 Flash

Full profiles: Gemini 3.6 Flash (Google) and Gemini 3.7 Flash (Google): every benchmark, price and rank.

Updated · Data from 11 sources

As of 16 Nov 2026, Gemini 3.6 Flash and Gemini 3.7 Flash are neck and neck on quality (61.0 vs 62.1 on the BenchLeader Index, inside the ±4.6 margin), and they cost about the same at $1.50 vs $1.50 per 1M tokens blended. Choose 3.6 Flash for agents & tools (59 vs 49), where it also streams ~2× faster; choose 3.7 Flash for fast first answers (2.2 s vs 11.0 s) and coding (62 vs 57), reasoning (68 vs 64), and maths (63 vs 59). Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 16 Nov 2026)

  • Gemini 3.6 Flash scores 61.0 on the BenchLeader Index and Gemini 3.7 Flash scores 62.1 (BenchLeader, 16 Nov 2026).
  • Gemini 3.6 Flash costs $1.50 per 1M tokens blended until 31 Dec 2026, then $3.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
  • Gemini 3.7 Flash costs $1.50 per 1M tokens blended (list price, 16 Nov 2026).
  • Gemini 3.6 Flash streams ~2× faster than Gemini 3.7 Flash (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 73 benchmarks both models have, Gemini 3.7 Flash leads 69 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Gemini 3.6 Flash is rated 1538 and Gemini 3.7 Flash 1588 (LMArena, as published by 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingGemini 3.7 Flash62 vs 57 category score; Arena WebDev 1588 vs 1538Medium
Agents & tool useGemini 3.6 Flash59 vs 49 category score; τ³-Banking (AA) 29.9% vs 32.8%High
MathsGemini 3.7 Flash63 vs 59 category score; FrontierMath Tiers 1–3 71.6% vs 59.0%Medium
ReasoningGemini 3.7 Flash68 vs 64 category score; GPQA Diamond 94.8% vs 94.1%Medium
KnowledgeGemini 3.7 Flash66 vs 64 category score; SimpleQA Verified 69.2% vs 66.2%Medium
Long documentsEither65 vs 66 category score; AA-LCR v1.1 80.0% vs 81.7%Either
Images and other mediaGemini 3.7 Flash67 vs 65 category score; Arena Vision 1313 vs 1297Medium
Chat quality (human preference)Either67 vs 68 on Arena votesEither
Lowest costEither$1.50 vs $1.50 per 1M blended; agentic coding session $0.060 vs $0.060; from 1 Jan 2027: $3.00 vs $1.50–
Fastest first answerGemini 3.7 Flash2.2 s (Gemini 3.7 Flash (high)) vs 11.0 s (Gemini 3.6 Flash (high)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Gemini 3.6 Flash (high) and Gemini 3.7 Flash (high) are neck and neck on quality (61.0 vs 62.1, within the ±4.6 margin).
  • Gemini 3.6 Flash (high) is stronger in agents & tools.
  • Gemini 3.7 Flash (high) is stronger in coding, human preference, knowledge, long context, maths, multimodal, reasoning.
  • They cost about the same ($1.50 per 1M blended) until 31 Dec 2026, then $3.00 vs $1.50 from 1 Jan 2027.
  • Gemini 3.6 Flash (high) streams 1.9× faster (177 vs 95 tokens per second).

At a glance

SpecGemini 3.6 FlashGemini 3.7 Flash
DeveloperGoogleGoogle
Released21 Jul 202613 Aug 2026
Context window (tokens)1,048,5761,048,576
Compared atGemini 3.6 Flash (high)Gemini 3.7 Flash (high)
Open weightsNoNo
Price in / out / cached input per 1M$0.750 / $3.75 / $0.075$0.750 / $3.75 / $0.075
Announced price change$1.50 / $7.50 / $0.150 from 1 Jan 2027None announced

Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGemini 3.6 Flash (high)Gemini 3.7 Flash (high)Leader
Reasoning63.667.8Gemini 3.7 Flash
Coding56.762.3Gemini 3.7 Flash
Agents & tools59.248.9Gemini 3.6 Flash
Maths59.062.6Gemini 3.7 Flash
Knowledge63.665.9Gemini 3.7 Flash
Human preference67.368.1level
Multimodal65.067.2Gemini 3.7 Flash
Long context64.665.5level

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceGemini 3.6 Flash, Reasoning: 63.6Gemini 3.6 Flash, Coding: 56.7Gemini 3.6 Flash, Agents & tools: 59.2Gemini 3.6 Flash, Maths: 59.0Gemini 3.6 Flash, Knowledge: 63.6Gemini 3.6 Flash, Long context: 64.6Gemini 3.6 Flash, Multimodal: 65.0Gemini 3.6 Flash, Human preference: 67.3Gemini 3.7 Flash, Reasoning: 67.8Gemini 3.7 Flash, Coding: 62.3Gemini 3.7 Flash, Agents & tools: 48.9Gemini 3.7 Flash, Maths: 62.6Gemini 3.7 Flash, Knowledge: 65.9Gemini 3.7 Flash, Long context: 65.5Gemini 3.7 Flash, Multimodal: 67.2Gemini 3.7 Flash, Human preference: 68.1

Not drawn, measured for fewer than two of these models: Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 73 benchmarks both have, Gemini 3.6 Flash leads 3, Gemini 3.7 Flash leads 69 and 1 is a tie. Every overall index that rates both puts Gemini 3.7 Flash ahead.

Overall indexGemini 3.6 Flash (high)Gemini 3.7 Flash (high)Leader
BenchLeader Index61.062.1neck and neck
Arena Text14831489Gemini 3.7 Flash

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGemini 3.6 Flash (high)Gemini 3.7 Flash (high)
Blended price per 1M tokens, until 31 Dec 2026$1.50$1.50
Input / output per 1M$0.750 / $3.75$0.750 / $3.75
Blended price per 1M from 1 Jan 2027$3.00$1.50
Input / output per 1M from 1 Jan 2027$1.50 / $7.50$0.750 / $3.75
Cached input per 1M$0.075$0.075
Price per task: chat reply$0.0014$0.0014
Price per task: summarize a 30-page report$0.011$0.011
Price per task: code edit$0.010$0.010
Price per task: agentic coding session$0.060$0.060
Price per task: structured extraction$0.0023$0.0023
Agentic coding session, input mostly cached$0.030$0.030
Output speed177 tok/s95 tok/s
Time to first answer11.0 s2.2 s
Time to a complete answer, last measured 13 Nov 202630.3 s–

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.6 Flash (high) scores 61.0 and takes 11 s to its first answer token; Gemini 3.6 Flash scores 49.3 in 1 s. Gemini 3.7 Flash (high) scores 62.1 and takes 2 s to its first answer token; Gemini 3.7 Flash (medium) scores 60.1 in 2 s, Gemini 3.7 Flash (low) scores 57.3 in 2 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

111 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGemini 3.6 Flash (high)Gemini 3.7 Flash (high)
BenchLeader IndexBenchLeader61.062.1
Agents & tools scoreBenchLeader59.248.9
Coding scoreBenchLeader56.762.3
Human preference scoreBenchLeader67.368.1
Knowledge scoreBenchLeader63.665.9
Long context scoreBenchLeader64.665.5
Maths scoreBenchLeader59.062.6
Multimodal scoreBenchLeader65.067.2
Reasoning scoreBenchLeader63.667.8
Blended price $/MBenchLeader$1.50$1.50
Output speedBenchLeader177 tok/s95 tok/s
Time to first answerBenchLeader11.0 s2.2 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.1%94.8%
Arena Hard PromptsArena (LMArena)15011510
LiveBench 1.0 ReasoningLiveBench85.2%87.8%
GPQA Diamond (AA)Artificial Analysis92.8%94.5%
Humanity's Last Exam (AA)Artificial Analysis40.8%47.9%
GPQA Diamond (Vals)Vals AI93.4%93.9%
ARC-AGI-1ARC Prize91.2%95.5%
ARC-AGI-2ARC Prize60.4%84.6%
CritPtArtificial Analysis10.6%14.3%
Arena ExpertArena (LMArena)15001519
Chess PuzzlesEpoch AI Benchmarking Hub40.0%66.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub30.0%37.0%
LMCAEpoch AI Benchmarking Hub44.9%50.4%
DTBenchEpoch AI Benchmarking Hub95.5%96.8%
ForecastBenchForecastBench65.7%†66.2%
Coding
SciCodeSciCode53.4%57.2%
WeirdMLWeirdML56.1%–
FrontierCodeCognition34.4%†43.6%†
Arena CodingArena (LMArena)15181520
Arena WebDevArena (LMArena)15381588
LiveBench 1.0 CodingLiveBench77.9%78.9%
LiveCodeBenchVals AI88.1%88.7%
IOIVals AI35.1%67.8%
SWE-bench (Vals)Vals AI79.6%80.8%
Code MigrationVals AI30.9%34.8%
Show all 111 benchmarks
MetricPublisherGemini 3.6 Flash (high)Gemini 3.7 Flash (high)
Coding
ProgramBenchVals AI0.0%0.0%
Vibe Code Bench v1.1Vals AI64.0%70.4%
MirrorCodeEpoch AI Benchmarking Hub23.3%41.1%
DeepSWE v1.1Epoch AI Benchmarking Hub46.7%65.3%
ALE-BenchEpoch AI Benchmarking Hub715.5904.3
FrontierSWEEpoch AI Benchmarking Hub–20.3%
Terminal-Bench 4.0 (AA)Artificial Analysis7.1%13.6%
Terminal-Bench 2.1 (AA)Artificial Analysis77.5%85.8%
GameBench 2 OverallDuelLab GameBench 250.6†–
GameBench 2 by reasoning settingDuelLab GameBench 263.0–
Design Arena WebsiteDesign Arena1292†1295†
Agents & tools
Terminal-BenchTerminal-Bench–12.4%
Remote Labor IndexScale AI / CAIS–5.0%†
APEX-AgentsMercor46.9%†67.8%†
Arena AgentArena (LMArena)–-2.2
LiveBench Agentic CodingLiveBench43.4%58.3%
Terminal-Bench 2.1 (Vals)Vals AI73.8%77.5%
GDPval-AA v2.1Artificial Analysis12931404
τ³-Banking (AA)Artificial Analysis29.9%32.8%
Analyst Agent (AA)Artificial Analysis–60.0%
CyberBenchVals AI45.4%43.8%
Finance Agent v2Vals AI56.3%59.0%
Harvey's Legal Agent Benchmark v1Vals AI3.3%8.8%
Legal Research BenchVals AI25.0%34.6%
SkillsBenchVals AI–65.9%
SREBenchVals AI–4.6%
Tax Agent BenchVals AI18.0%22.8%
Terminal-Bench 4.0 (Vals)Vals AI–12.1%
Terminal-Bench ScienceVals AI4.3%7.1%
Arena Agent Task CompletionArena (LMArena)–-3.5
AutomationBenchArtificial Analysis53.0%62.0%
GDP.pdf (AA)Artificial Analysis17.4%23.6%
EnterpriseOps-GymArtificial Analysis–50.4%†
AA-Briefcase v1.1Artificial Analysis9571115
Design Arena AgenticDesign Arena1177†1222†
FACTS SearchGoogle75.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.0%71.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub21.9%36.6%
OTIS Mock AIMEEpoch AI Benchmarking Hub94.2%97.2%
ProofBenchVals AI36.0%†58.0%†
LiveBench MathematicsLiveBench86.4%93.5%
AIME 2026MathArena96.7%†–
HMMT February 2026MathArena89.4%†–
MathArena ApexMathArena26.0%†–
Arena MathsArena (LMArena)15011502
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub66.2%69.2%
LiveBench 1.0 Data AnalysisLiveBench63.0%68.0%
MMLU-ProVals AI89.3%90.1%
LegalBenchVals AI86.7%87.3%
CorpFinVals AI63.3%–
TaxEvalVals AI74.9%74.7%
BioMysteryBenchVals AI58.5%–
Excel Modeling BenchmarkVals AI65.4%71.3%
MedCodeVals AI53.1%53.4%
MedScribeVals AI79.7%83.9%
Public Benefits Bench v1.1Vals AI56.6%–
Financial Coaching BenchVals AI65.8%–
GDP.pdfEpoch AI Benchmarking Hub14.0%23.8%
FACTS ParametricGoogle73.9%†–
Instruction following
LiveBench LanguageLiveBench83.9%85.5%
LiveBench Instruction FollowingLiveBench75.4%79.9%
Arena Instruction FollowingArena (LMArena)14731486
Human preference
Arena TextArena (LMArena)14831489
EQ-Bench Creative Writing v3EQ-Bench1602†1720†
Arena Creative WritingArena (LMArena)14711487
Arena Multi-turnArena (LMArena)14901490
Arena Longer QueriesArena (LMArena)14851501
Multimodal
Arena VisionArena (LMArena)12971313
MMMU-ProArtificial Analysis83.2%85.5%
MMMU-Pro (Vals)Vals AI88.4%89.0%
MortgageTaxVals AI67.6%66.7%
Humanity's Sixth SenseScale AI SEAL31.9%39.8%
Blueprint-Bench 2Epoch AI Benchmarking Hub31.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub23.3%26.7%
FACTS MultimodalGoogle53.7%†–
Long context
AA-LCR v1.1Artificial Analysis80.0%81.7%
Arena DocumentArena (LMArena)14541468
MLCRArtificial Analysis10.0%12.2%
FACTS GroundingGoogle66.6%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub155.2†158.4†
LiveBench 1.0LiveBench73.6%78.8%
AA Intelligence Index v4.3.2Artificial Analysis34.039.1
AA Progress Index v1Artificial Analysis305.7317.4
Vals RSI IndexVals AI–18.3%
Vals Multimodal IndexVals AI65.1%–
Safety & honesty
DistressBenchScale AI SEAL–69.0%†

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 3.6 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
  • Gemini 3.6 Flash (high): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1); 1 score revision.
  • Gemini 3.7 Flash (high): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • Gemini 3.6 Flash (high): 1 new result (MirrorCode); 1 score revision.
  • Gemini 3.7 Flash (high): BenchLeader Index 62.6 → 62.1.
  • Gemini 3.7 Flash (high): 1 score revision.
  • Gemini 3.7 Flash (high): 1 new result (Arena Document).
  • Gemini 3.6 Flash (high): 1 score revision.
  • Gemini 3.7 Flash (high): 1 new result (MirrorCode).
  • Gemini 3.6 Flash (high): BenchLeader Index 61.8 → 61.2.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Gemini 3.6 Flash vs Gemini 3.7 Flash: questions

Is Gemini 3.6 Flash better than Gemini 3.7 Flash?
Gemini 3.6 Flash (high) and Gemini 3.7 Flash (high) are neck and neck on quality (61.0 vs 62.1, within the ±4.6 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Gemini 3.6 Flash vs Gemini 3.7 Flash: which is cheaper, and will that change?
They cost the same: $1.50 per million tokens blended. Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.
Is Gemini 3.6 Flash or Gemini 3.7 Flash better for coding?
Gemini 3.7 Flash scores higher in coding (62 vs 57 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1538 for Gemini 3.6 Flash against 1588 for Gemini 3.7 Flash.
Which is faster, Gemini 3.6 Flash or Gemini 3.7 Flash?
Gemini 3.6 Flash streams ~2× faster (177 vs 95 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.6 Flash or Gemini 3.7 Flash better for agents and tool use?
Gemini 3.6 Flash scores higher in agentic tasks (59 vs 49 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 29.9% for Gemini 3.6 Flash against 32.8% for Gemini 3.7 Flash.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (65 vs 66). Both accept 1,048,576 tokens of context.
Which has lower latency?
Gemini 3.7 Flash answers first: 2.2 s against 11.0 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Gemini 3.6 Flash vs Gemini 3.7 Flash?
Across the 73 benchmarks both have, Gemini 3.6 Flash leads 3, Gemini 3.7 Flash leads 69 and 1 is a tie. Every overall index that rates both puts Gemini 3.7 Flash ahead.
When was Gemini 3.7 Flash released?
Gemini 3.7 Flash was released on 13 Aug 2026.