BenchLeader

Gemini 3.1 Pro vs Gemini 3.8 Flash

Full profiles: Gemini 3.1 Pro (Google) and Gemini 3.8 Flash (Google): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, Gemini 3.1 Pro and Gemini 3.8 Flash are neck and neck on quality (60.4 vs 60.2 on the BenchLeader Index, inside the ±6.0 margin), and Gemini 3.8 Flash is 3.0× cheaper at $1.50 vs $4.50 per 1M tokens blended. Choose 3.1 Pro for knowledge (66 vs 58), coding (59 vs 52), and reasoning (65 vs 59); choose 3.8 Flash for agents & tools (75 vs 57). Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 16 Nov 2026)

  • Gemini 3.1 Pro scores 60.4 on the BenchLeader Index and Gemini 3.8 Flash scores 60.2 (BenchLeader, 16 Nov 2026).
  • Gemini 3.1 Pro costs $4.50 per 1M tokens blended (list price, 16 Nov 2026).
  • Gemini 3.8 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).
  • Of the 3 benchmarks both models have, Gemini 3.1 Pro leads 2 (BenchLeader, 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 3.1 Pro59 vs 52 category scoreMedium
Agents & tool useGemini 3.8 Flash75 vs 57 category scoreHigh
ReasoningGemini 3.1 Pro65 vs 59 category score; LMCA 53.8% vs 52.9%Medium
KnowledgeGemini 3.1 Pro66 vs 58 category score; GDP.pdf 17.0% vs 23.4%High
Lowest costGemini 3.8 Flash$1.50 vs $4.50 per 1M blended; agentic coding session $0.060 vs $0.168; from 1 Jan 2027: $3.00 vs $4.50–
Fastest first answerEither15.2 s (Gemini 3.1 Pro (high)) vs 14.8 s (Gemini 3.8 Flash (medium)) 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 3.1 Pro (high) and Gemini 3.8 Flash (medium) are neck and neck on quality (60.4 vs 60.2, within the ±6.0 margin).
  • Gemini 3.1 Pro (high) is stronger in coding, knowledge, reasoning.
  • Gemini 3.8 Flash (medium) is stronger in agents & tools.
  • Gemini 3.8 Flash (medium) is 3.0× cheaper ($1.50 vs $4.50 per 1M blended) until 31 Dec 2026, then $3.00 vs $4.50 from 1 Jan 2027.

At a glance

SpecGemini 3.1 ProGemini 3.8 Flash
DeveloperGoogleGoogle
Released19 Feb 20262 Sep 2026
Context window (tokens)1,048,5761,048,576
Compared atGemini 3.1 Pro (high)Gemini 3.8 Flash (medium)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $12.00 / $0.200$0.750 / $3.75 / $0.075
Announced price changeNone announced$1.50 / $7.50 from 1 Jan 2027

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 3.1 Pro (high)Gemini 3.8 Flash (medium)Leader
Reasoning64.758.7Gemini 3.1 Pro
Coding58.651.6Gemini 3.1 Pro
Agents & tools56.775.0Gemini 3.8 Flash
Maths65.7–not comparable
Knowledge65.657.7Gemini 3.1 Pro
Multimodal–66.7not comparable
Long context–66.7not comparable

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 & toolsKnowledgeGemini 3.1 Pro, Reasoning: 64.7Gemini 3.1 Pro, Coding: 58.6Gemini 3.1 Pro, Agents & tools: 56.7Gemini 3.1 Pro, Knowledge: 65.6Gemini 3.8 Flash, Reasoning: 58.7Gemini 3.8 Flash, Coding: 51.6Gemini 3.8 Flash, Agents & tools: 75.0Gemini 3.8 Flash, Knowledge: 57.7

Not drawn, measured for fewer than two of these models: Maths, Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 3 benchmarks both have, Gemini 3.1 Pro leads 2, Gemini 3.8 Flash leads 1. Every overall index that rates both puts Gemini 3.8 Flash ahead.

Overall indexGemini 3.1 Pro (high)Gemini 3.8 Flash (medium)Leader
BenchLeader Index60.460.2neck and neck
Arena Text1487†1497Gemini 3.8 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 3.1 Pro (high)Gemini 3.8 Flash (medium)
Blended price per 1M tokens, until 31 Dec 2026$4.50$1.50
Input / output per 1M$2.00 / $12.00$0.750 / $3.75
Blended price per 1M from 1 Jan 2027$4.50$3.00
Input / output per 1M from 1 Jan 2027$2.00 / $12.00$1.50 / $7.50
Cached input per 1M$0.200$0.075
Price per task: chat reply$0.0044$0.0014
Price per task: summarize a 30-page report$0.031$0.011
Price per task: code edit$0.030$0.010
Price per task: agentic coding session$0.168$0.060
Price per task: structured extraction$0.0064$0.0023
Agentic coding session, input mostly cached$0.087$0.030
Cost per benchmark task (AA Index)–$6.26
Output tokens per task (AA Index)–82k
Of which reasoning–47k
Time per task (AA Index)–12 min
Output speed111 tok/s116 tok/s
Time to first answer15.2 s14.8 s
Time to a complete answer, last measured 13 Nov 202637.5 s41.8 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.1 Pro (high) scores 60.4 and takes 15 s to its first answer token; Gemini 3.1 Pro scores 59.9 in 15 s. Gemini 3.8 Flash (medium) scores 60.2 and takes 15 s to its first answer token; Gemini 3.8 Flash (high) scores 59.4 in 20 s, Gemini 3.8 Flash scores 56.4 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

219 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 3.1 Pro (high)Gemini 3.8 Flash (medium)
BenchLeader IndexBenchLeader60.460.2
Agents & tools scoreBenchLeader56.775.0
Coding scoreBenchLeader58.651.6
Knowledge scoreBenchLeader65.657.7
Maths scoreBenchLeader65.7–
Reasoning scoreBenchLeader64.758.7
Long context scoreBenchLeader–66.7
Multimodal scoreBenchLeader–66.7
Blended price $/MBenchLeader$4.50$1.50
Output speedBenchLeader111 tok/s116 tok/s
Time to first answerBenchLeader15.2 s14.8 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.4%95.4%†
Humanity's Last ExamScale AI / CAIS46.4%†44.5%†
SimpleBenchSimpleBench79.6%†82.4%†
Arena Hard PromptsArena (LMArena)1508†1518†
LiveBench 2.0 ReasoningLiveBench–89.3%†
LiveBench 1.0 ReasoningLiveBench84.0%89.3%†
GPQA Diamond (AA)Artificial Analysis94.1%†93.5%
Humanity's Last Exam (AA)Artificial Analysis47.0%†42.1%
HLE-Diamond (AA)Artificial Analysis31.4%†29.1%
GPQA Diamond (Vals)Vals AI95.5%94.4%†
EnigmaEvalScale AI SEAL36.8%–
ARC-AGI-1ARC Prize98.0%†97.5%
ARC-AGI-2ARC Prize77.1%†82.9%
ARC-AGI-3ARC Prize0.4%†24.2%
CritPtArtificial Analysis17.7%†12.3%
CritPt v2 hard subset (AA)Artificial Analysis–45.0%
MysteryMechanismVals AI20.7%36.5%†
HLE-Diamond (Scale)Scale AI SEAL–34.3%†
Arena ExpertArena (LMArena)1509†1527†
Chess PuzzlesEpoch AI Benchmarking Hub51.0%58.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub34.0%47.0%†
CL-benchEpoch AI Benchmarking Hub20.8%†–
CL-bench LifeEpoch AI Benchmarking Hub16.9%†–
LMCAEpoch AI Benchmarking Hub53.8%52.9%
DTBenchEpoch AI Benchmarking Hub95.5%94.9%
Show all 219 benchmarks
MetricPublisherGemini 3.1 Pro (high)Gemini 3.8 Flash (medium)
Reasoning
ForecastBenchForecastBench65.2%–
Coding
SciCodeSciCode58.7%†55.1%
WeirdMLWeirdML72.1%†84.8%†
FrontierCodeCognition–41.2%
GSO-BenchGSO-Bench22.6%†–
Arena CodingArena (LMArena)1520†1531†
Arena WebDevArena (LMArena)1446†1584†
LiveBench 2.0 CodingLiveBench–73.3%†
LiveBench 1.0 CodingLiveBench76.5%72.5%†
LiveCodeBenchVals AI88.5%89.5%†
IOIVals AI51.8%56.9%†
SWE-bench (Vals)Vals AI78.8%80.0%†
SWE-Bench ProScale AI SEAL46.1%†–
Code MigrationVals AI17.3%36.5%†
Code Migration v1.1Vals AI–38.6%†
ProgramBenchVals AI0.0%1.0%†
SWE-bench MultimodalVals AI–40.8%†
Vibe Code Bench 1-100Vals AI6.7%18.8%†
Vibe Code Bench v1.1Vals AI32.0%78.7%†
SWE-Bench Pro (private)Scale AI SEAL32.2%†–
SWE Atlas v1.0: Codebase QnAScale AI SEAL13.5%†47.0%†
SWE Atlas v1.0: RefactoringScale AI SEAL33.8%†44.8%†
SWE Atlas v1.0: Test WritingScale AI SEAL29.8%†53.7%†
SWE Atlas v1.1Scale AI SEAL–57.3%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL–45.2%†
SWE Atlas v1.1: Test WritingScale AI SEAL–71.1%†
SWE Atlas v1.1: RefactoringScale AI SEAL–55.7%†
SWE-Bench Pro V2Scale AI SEAL–94.9%†
SWE-Bench Pro V2 HARDScale AI SEAL–58.8%†
MirrorCodeEpoch AI Benchmarking Hub8.9%38.9%†
Surface Evolver BenchEpoch AI Benchmarking Hub–76.9%†
DeepSWE v1.1Epoch AI Benchmarking Hub11.7%†71.0%
CursorBenchCursor–37.3%
ALE-BenchEpoch AI Benchmarking Hub1160.6†1269.7†
AlgoTuneAlgoTune2.0†–
FrontierSWEEpoch AI Benchmarking Hub–19.6%†
WeirdML v3WeirdML–7.4%†
Terminal-Bench 4.0 (AA)Artificial Analysis4.0%†19.7%
Terminal-Bench 2.1 (AA)Artificial Analysis73.8%†83.9%
Startrise FrontendStartrise–64.6%†
GameBench 2 OverallDuelLab GameBench 2–59.0†
GameBench 2 by reasoning settingDuelLab GameBench 2–59.7
Design Arena WebsiteDesign Arena1226†1291†
FrontierCode 1.1 (AA)Artificial Analysis–37.1%
FrontierCode 2.0 (AA)Artificial Analysis–16.5%
Agents & tools
Terminal-BenchTerminal-Bench80.2%†18.2%†
Remote Labor IndexScale AI / CAIS–5.8%†
APEX-AgentsMercor35.1%†64.3%†
Arena AgentArena (LMArena)-4.5†2.3†
LiveBench Long AgenticLiveBench–16.5%†
LiveBench BrowserLiveBench–45.1%†
LiveBench Agentic CodingLiveBench44.1%54.2%†
Terminal-Bench HardArtificial Analysis53.8%†–
τ²-Bench Telecom (AA)Artificial Analysis95.6%†–
Terminal-Bench 2.1 (Vals)Vals AI70.8%81.3%†
MCP AtlasScale AI SEAL78.2%–
HiL-BenchScale AI SEAL35.3%†41.5%†
τ³-bench Bankingτ²-bench26.0%–
GDPval-AA v2.1, normalised scoreArtificial Analysis14.6%†46.1%
GDPval-AA v2.1Artificial Analysis799†1432
τ³-Banking (AA)Artificial Analysis21.4%†45.8%
ITBench SRE (AA)Artificial Analysis30.3%†52.5%†
Analyst Agent (AA)Artificial Analysis41.3%†46.3%†
APEX-Agents (AA)Artificial Analysis32.0%†–
CUA-benchVals AI–4.2%†
CyberBenchVals AI–43.8%†
Finance Agent v2Vals AI43.0%61.4%†
Finance Agent v2.1Vals AI–65.8%†
Harvey's Legal Agent Benchmark v1.1Vals AI–12.1%†
Harvey's Legal Agent Benchmark v1Vals AI0.0%10.0%†
Legal Research BenchVals AI20.7%38.9%†
SkillsBenchVals AI–58.0%†
SREBenchVals AI0.0%11.1%†
Tax Agent BenchVals AI9.3%32.1%†
Terminal-Bench 2.0 (Vals)Vals AI67.4%–
Terminal-Bench 4.0 (Vals)Vals AI2.5%19.7%†
Terminal-Bench ScienceVals AI1.4%8.6%†
Time Horizon Index: KSPVals AI–18.8%†
Arena SearchArena (LMArena)1209†–
Arena Agent Task CompletionArena (LMArena)-11.3†1.3†
BALROGBALROG57.0%†–
DeepResearch BenchDeepResearch Bench47.8%–
PostTrainBenchEpoch AI Benchmarking Hub18.1%†–
ExploitBenchEpoch AI Benchmarking Hub26.1%†–
METR Time HorizonsMETR77.0%†–
GBAEvalEpoch AI Benchmarking Hub0.8%†–
Vending-Bench 2Andon Labs911.2†5093.8†
AutomationBenchArtificial Analysis35.4%†60.9%
GDP.pdf (AA)Artificial Analysis17.8%†22.8%
Harvey LAB-AA v1.1Harvey0.0%†0.0%†
EnterpriseOps-GymArtificial Analysis42.2%†–
AA-Briefcase v1.1Artificial Analysis457†1183
Design Arena AgenticDesign Arena1088†1225†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–10.5%
CWE-Bench (AA)Artificial Analysis–52.5%†
DeepSec-Bench (AA)Artificial Analysis–14.5%†
CyberGym end-to-end (AA)Artificial Analysis–8.4%†
MKA (AA)Artificial Analysis–35.3%†
BrowseCompOpenAI31.2%†–
DeepSearchQAGoogle60.2%†–
FACTS SearchGoogle90.2%†80.4%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.6%†68.4%†
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%†21.9%†
OTIS Mock AIMEEpoch AI Benchmarking Hub95.6%98.9%†
ProofBenchVals AI26.0%†48.0%†
LiveBench MathematicsLiveBench91.0%91.6%†
AIME (Vals)Vals AI98.1%–
AIME 2026MathArena98.3%–
HMMT February 2026MathArena94.7%–
USAMO 2026MathArena74.4%–
MathArena ApexMathArena60.9%–
Arena MathsArena (LMArena)1488†1519†
FrontierMath ErdősEpoch AI Benchmarking Hub–0.0%†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub73.5%69.7%†
LiveBench 2.0 Data AnalysisLiveBench–54.0%†
LiveBench ResearchLiveBench–79.4%†
LiveBench 1.0 Data AnalysisLiveBench78.5%54.0%†
AA-Omniscience v1.1Artificial Analysis–23.7
MMLU-ProVals AI91.0%90.2%†
LegalBenchVals AI87.4%87.0%†
CorpFinVals AI64.5%–
TaxEvalVals AI72.9%74.5%†
MedQAVals AI96.4%–
PRBench FinanceScale AI SEAL41.9%†49.5%†
PRBench LegalScale AI SEAL44.0%†48.9%†
MultiNRCScale AI SEAL64.7%†–
BioMysteryBenchVals AI60.0%62.2%†
CaseLaw v2Vals AI64.8%–
Excel Modeling BenchmarkVals AI52.6%72.2%†
Excel Modeling Benchmark v1.1Vals AI–72.9%†
MedCodeVals AI59.1%48.1%†
MedScribeVals AI76.1%84.5%†
Public Benefits Bench v1.1Vals AI53.8%65.3%†
Access to Justice BenchmarkVals AI–67.1%†
Financial Coaching BenchVals AI66.7%66.3%†
Immigration BenchVals AI–63.4%†
DrugDiscoveryBenchScale AI SEAL41.9%–
EBR-benchEpoch AI Benchmarking Hub14.3%†–
GDP.pdfEpoch AI Benchmarking Hub17.0%23.4%
AA-Omniscience v1.1: accuracyArtificial Analysis–49.6%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–48.5%
Global-MMLU-Lite (AA)Artificial Analysis93.2%†–
HealthBench Professional (AA)OpenAI–51.7%†
FACTS ParametricGoogle79.4%†78.7%†
Instruction following
LiveBench LanguageLiveBench85.4%87.8%†
LiveBench Instruction FollowingLiveBench79.1%81.4%†
IFBenchArtificial Analysis77.1%†–
MultiChallengeScale AI SEAL71.4%†–
TutorBenchScale AI SEAL53.0%†–
Arena Instruction FollowingArena (LMArena)1480†1492†
Human preference
Arena TextArena (LMArena)1487†1497†
EQ-Bench 4EQ-Bench1132†–
EQ-Bench Creative Writing v3EQ-Bench1491†1744†
Arena Creative WritingArena (LMArena)1482†1488†
Arena Multi-turnArena (LMArena)1495†1505†
Arena Longer QueriesArena (LMArena)1499†1511†
Multimodal
Arena VisionArena (LMArena)1296†1317†
LiveBench DesignLiveBench–69.7%†
MMMU-ProArtificial Analysis82.4%†84.2%
MMMU-Pro (Vals)Vals AI88.2%89.1%†
MortgageTaxVals AI69.4%65.3%†
SAGEVals AI83.2%88.2%†
AudioMCScale AI SEAL–60.4%†
AudioMC (text output)Scale AI SEAL–60.4%†
Humanity's Sixth SenseScale AI SEAL–41.6%†
VTBScale AI SEAL29.0%†–
GeoBenchGeoBench84.0%†86.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub26.5%†38.6%†
Furniture AssemblyEpoch AI Benchmarking Hub26.7%31.7%†
VIALS-AAHandshake AI–41.0%†
Code2Video-AAArtificial Analysis–899†
AA-3DArtificial Analysis–974†
FACTS MultimodalGoogle50.4%†57.6%†
Long context
AA-LCR v1.1Artificial Analysis82.0%†84.0%
Arena DocumentArena (LMArena)1459†1469†
MLCRArtificial Analysis11.1%†12.8%
FACTS GroundingGoogle56.6%†68.2%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.2†158.8†
LiveBench 2.0LiveBench–57.3%†
LiveBench 1.0LiveBench77.0%75.8%†
AA Intelligence Index v5.0.1Artificial Analysis–30.1
AA Intelligence Index v4.3.2Artificial Analysis29.7†39.8
AA Progress Index v1Artificial Analysis296.1†319.1
Vals IndexVals AI–56.0†
Vals Finance IndexVals AI–60.5%†
Vals RSI IndexVals AI–19.9%†
Vals Science IndexVals AI27.4%35.8%†
Vals Multimodal IndexVals AI56.1%–
Vals Router IndexVals AI–56.0%†
Vals Legal IndexVals AI–69.8%†
AA Cyber IndexArtificial Analysis–25.1†
Safety & honesty
FORTRESSScale AI SEAL29.8%†–
MASKScale AI SEAL42.4%†–
DistressBenchScale AI SEAL68.8%†70.7%†

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 3.8 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
  • Gemini 3.8 Flash (medium): 1 score revision.
  • Gemini 3.1 Pro (high): 4 new results (AIME 2026, HMMT February 2026, USAMO 2026…).
  • Gemini 3.8 Flash (medium): 2 score revisions.
  • Gemini 3.8 Flash (medium): 1 score revision.
  • Gemini 3.8 Flash (medium): 1 new result (AA-Briefcase v1.1).
  • Gemini 3.8 Flash (medium): BenchLeader Index 63.4 → 60.4.
  • Gemini 3.1 Pro (high): 1 score revision.
  • Gemini 3.8 Flash (medium): 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 2 score revisions; cost per task moved from $2.59/M to $6.26/M (141% up).
  • Gemini 3.1 Pro (high): cost per task moved from $1.30/M to $1.44/M (11% up).

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

Gemini 3.1 Pro vs Gemini 3.8 Flash: questions

Is Gemini 3.1 Pro better than Gemini 3.8 Flash?
Gemini 3.1 Pro (high) and Gemini 3.8 Flash (medium) are neck and neck on quality (60.4 vs 60.2, within the ±6.0 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 3.1 Pro vs Gemini 3.8 Flash: which is cheaper, and will that change?
Gemini 3.8 Flash is cheaper today: $1.50 against $4.50 per million tokens, blended at three input tokens per output token. Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.
Is Gemini 3.1 Pro or Gemini 3.8 Flash better for coding?
Gemini 3.1 Pro scores higher in coding (59 vs 52 on the category index, where 50 is average).
Which is faster, Gemini 3.1 Pro or Gemini 3.8 Flash?
Gemini 3.8 Flash streams faster (116 vs 111 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.1 Pro or Gemini 3.8 Flash better for agents and tool use?
Gemini 3.8 Flash scores higher in agentic tasks (75 vs 57 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Both accept 1,048,576 tokens of context.
Which has lower latency?
Gemini 3.8 Flash answers first: 14.8 s against 15.2 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 3.1 Pro vs Gemini 3.8 Flash?
Across the 3 benchmarks both have, Gemini 3.1 Pro leads 2, Gemini 3.8 Flash leads 1. Every overall index that rates both puts Gemini 3.8 Flash ahead.
When was Gemini 3.8 Flash released?
Gemini 3.8 Flash was released on 2 Sep 2026.