BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases4

Gemini 3.6 Flash vs o3

Full profiles: Gemini 3.6 Flash (Google) and o3 (OpenAI): every benchmark, price and rank.

Updated · Data from 17 sources

As of 2 Nov 2026, Gemini 3.6 Flash and o3 are neck and neck on quality (61.3 vs 61.0 on the BenchLeader Index, inside the ±4.5 margin), and Gemini 3.6 Flash is 2.3× cheaper at $1.50 vs $3.50 per 1M tokens blended. Choose Gemini 3.6 Flash for multimodal (65 vs 57), knowledge (64 vs 56), and human preference (67 vs 61), where it also streams faster; choose o3 for fast first answers (6.8 s vs 16.4 s) and maths (71 vs 59), agents & tools (70 vs 59), and coding (62 vs 57). Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 2 Nov 2026)

  • Gemini 3.6 Flash scores 61.3 on the BenchLeader Index and o3 scores 61.0 (BenchLeader, 2 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).
  • o3 costs $3.50 per 1M tokens blended (list price, 2 Nov 2026).
  • Gemini 3.6 Flash streams faster than o3 (Artificial Analysis, 7-day median, 2 Nov 2026).
  • Of the 14 benchmarks both models have, Gemini 3.6 Flash leads 14 (BenchLeader, 2 Nov 2026).
Gemini 3.6 Flash benchmarks high Google o3 benchmarks OpenAIAdd a third model

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
Codingo362 vs 57 category score; Arena Coding 1460 vs 1518Medium
Agents & tool useo370 vs 59 category scoreHigh
Mathso371 vs 59 category score; Arena Maths 1448 vs 1504High
ReasoningGemini 3.6 Flash64 vs 61 category score; Arena Hard Prompts 1501 vs 1441Medium
KnowledgeGemini 3.6 Flash64 vs 56 category scoreHigh
Long documentsGemini 3.6 Flash65 vs 62 category score; AA-LCR v1.1 80.0% vs 74.7%Medium
Images and other mediaGemini 3.6 Flash65 vs 57 category score; Arena Vision 1299 vs 1214High
Chat quality (human preference)Gemini 3.6 Flash67 vs 61 on Arena votesMedium
Lowest costGemini 3.6 Flash$1.50 vs $3.50 per 1M blended; agentic coding session $0.060 vs $0.152; from 1 Jan 2027: $3.00 vs $3.50–
Fastest first answero36.8 s (o3) vs 16.4 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 o3 are neck and neck on quality (61.3 vs 61.0, within the ±4.5 margin).
  • Gemini 3.6 Flash (high) is stronger in human preference, knowledge, long context, multimodal, reasoning.
  • o3 is stronger in agents & tools, coding, maths, instruction following.
  • Gemini 3.6 Flash (high) is 2.3× cheaper ($1.50 vs $3.50 per 1M blended) until 31 Dec 2026, then $3.00 vs $3.50 from 1 Jan 2027.

At a glance

SpecGemini 3.6 Flasho3
DeveloperGoogleOpenAI
Released21 Jul 202616 Apr 2025
Context window (tokens)1,048,576200,000
Compared atGemini 3.6 Flash (high)o3
Open weightsNoNo
Price in / out / cached input per 1M$0.750 / $3.75 / $0.075$2.00 / $8.00 / $0.500
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)o3Leader
Reasoning64.060.9Gemini 3.6 Flash
Coding56.961.8o3
Agents & tools59.370.3o3
Maths59.470.5o3
Knowledge63.856.1Gemini 3.6 Flash
Instruction following–65.1not comparable
Human preference67.461.1Gemini 3.6 Flash
Multimodal65.256.7Gemini 3.6 Flash
Long context64.862.1Gemini 3.6 Flash

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: 64.0Gemini 3.6 Flash, Coding: 56.9Gemini 3.6 Flash, Agents & tools: 59.3Gemini 3.6 Flash, Maths: 59.4Gemini 3.6 Flash, Knowledge: 63.8Gemini 3.6 Flash, Long context: 64.8Gemini 3.6 Flash, Multimodal: 65.2Gemini 3.6 Flash, Human preference: 67.4o3, Reasoning: 60.9o3, Coding: 61.8o3, Agents & tools: 70.3o3, Maths: 70.5o3, Knowledge: 56.1o3, Long context: 62.1o3, Multimodal: 56.7o3, Human preference: 61.1

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

ModelIndex

Where sources disagree

Across the 14 benchmarks both have, Gemini 3.6 Flash leads 14, o3 leads 0. Every overall index that rates both puts Gemini 3.6 Flash ahead.

Overall indexGemini 3.6 Flash (high)o3Leader
BenchLeader Index61.361.0neck and neck
Arena Text14831432Gemini 3.6 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)o3
Blended price per 1M tokens, until 31 Dec 2026$1.50$3.50
Input / output per 1M$0.750 / $3.75$2.00 / $8.00
Blended price per 1M from 1 Jan 2027$3.00$3.50
Input / output per 1M from 1 Jan 2027$1.50 / $7.50$2.00 / $8.00
Cached input per 1M$0.075$0.500
Price per task: chat reply$0.0014$0.0032
Price per task: summarize a 30-page report$0.011$0.029
Price per task: code edit$0.010$0.024
Price per task: agentic coding session$0.060$0.152
Price per task: structured extraction$0.0023$0.0056
Agentic coding session, input mostly cached$0.030$0.085
Output speed197 tok/s160 tok/s
Time to first answer16.4 s6.8 s
Time to a complete answer18.9 s9.9 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.6 Flash (high) scores 61.3 and takes 16 s to its first answer token; Gemini 3.6 Flash scores 49.5 in 1 s. o3 scores 61.0 and takes 7 s to its first answer token; o3 (high) scores 53.8 in 7 s, o3 (medium) scores 53.3 in 7 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

135 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)o3
BenchLeader IndexBenchLeader61.361.0
Agents & tools scoreBenchLeader59.370.3
Coding scoreBenchLeader56.961.8
Human preference scoreBenchLeader67.461.1
Knowledge scoreBenchLeader63.856.1
Long context scoreBenchLeader64.862.1
Maths scoreBenchLeader59.470.5
Multimodal scoreBenchLeader65.256.7
Reasoning scoreBenchLeader64.060.9
Instruction following scoreBenchLeader–65.1
Blended price $/MBenchLeader$1.50$3.50
Output speedBenchLeader197 tok/s160 tok/s
Time to first answerBenchLeader16.4 s6.8 s
Context windowBenchLeader1,048,576 tokens200,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.1%81.8%†
Humanity's Last ExamScale AI / CAIS–20.3%†
SimpleBenchSimpleBench–53.1%†
Arena Hard PromptsArena (LMArena)15011441
LiveBench 1.0 ReasoningLiveBench85.2%–
GPQA Diamond (AA)Artificial Analysis92.8%82.7%
Humanity's Last Exam (AA)Artificial Analysis40.8%20.1%
GPQA Diamond (Vals)Vals AI93.4%84.1%†
Kagi LLM BenchmarkKagi LLM Benchmark–67.6%
GPQA Diamond (HELM)HELM Capabilities–75.3%
ARC-AGI-1ARC Prize91.2%60.8%†
ARC-AGI-2ARC Prize60.4%6.5%†
CritPtArtificial Analysis10.6%1.1%
SciPredictScale AI SEAL–17.9%
Chess PuzzlesEpoch AI Benchmarking Hub40.0%36.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub30.0%29.0%†
CL-benchEpoch AI Benchmarking Hub–17.8%†
LMCAEpoch AI Benchmarking Hub44.9%39.7%†
DTBenchEpoch AI Benchmarking Hub95.5%84.8%†
ForecastBenchForecastBench65.9%†64.6%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–62.3%†
SciCodeSciCode53.4%–
WeirdMLWeirdML56.1%52.4%†
FrontierCodeCognition34.4%†–
GSO-BenchGSO-Bench–8.8%†
Show all 135 benchmarks
MetricPublisherGemini 3.6 Flash (high)o3
Coding
Arena CodingArena (LMArena)15181460
Arena WebDevArena (LMArena)1538–
LiveBench 1.0 CodingLiveBench77.9%–
LiveCodeBenchVals AI88.1%83.9%†
IOIVals AI35.1%–
SWE-bench (Vals)Vals AI79.6%–
Aider PolyglotAider polyglot leaderboard–81.3%
SWE-bench Verified (bash only)SWE-bench–58.4%
SWE-bench Verified (any scaffold)SWE-bench–58.4%
Code MigrationVals AI30.9%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI64.0%–
CadEvalEpoch AI Benchmarking Hub–74.0%†
DeepSWE v1.1Epoch AI Benchmarking Hub46.7%–
ALE-BenchEpoch AI Benchmarking Hub715.5933.5†
Terminal-Bench 4.0 (AA)Artificial Analysis7.1%–
Terminal-Bench 2.1 (AA)Artificial Analysis77.5%–
GameBench 2 OverallDuelLab GameBench 252.5†36.2
GameBench 2 by reasoning settingDuelLab GameBench 264.632.0†
LiveCodeBench (AA)Artificial Analysis–80.8%
Agents & tools
GDPvalOpenAI–30.8%†
APEX-AgentsMercor46.9%†–
LiveBench Agentic CodingLiveBench43.4%–
Terminal-Bench HardArtificial Analysis–37.1%
τ²-Bench Telecom (AA)Artificial Analysis–80.7%
Terminal-Bench 2.1 (Vals)Vals AI73.8%–
BFCL OverallBerkeley Function Calling Leaderboard–63.0%
τ³-Banking (AA)Artificial Analysis29.9%–
CyberBenchVals AI45.4%–
Finance Agent v2Vals AI56.3%–
Harvey's Legal Agent Benchmark v1Vals AI3.3%–
Legal Research BenchVals AI25.0%–
Tax Agent BenchVals AI18.0%–
Terminal-Bench ScienceVals AI4.3%–
DeepResearch BenchDeepResearch Bench–45.2%†
METR Time HorizonsMETR–63.6%
AutomationBenchArtificial Analysis53.0%–
GDP.pdf (AA)Artificial Analysis17.4%–
BrowseComp-PlusBrowseComp-Plus–50.5%
FACTS SearchGoogle68.2%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.0%33.3%†
FrontierMath Tier 4Epoch AI Benchmarking Hub21.9%–
OTIS Mock AIMEEpoch AI Benchmarking Hub94.2%83.9%†
MATH Level 5Epoch AI Benchmarking Hub–97.8%†
ProofBenchVals AI36.0%†–
LiveBench MathematicsLiveBench86.4%–
AIME (Vals)Vals AI–85.3%†
MGSMVals AI–91.8%†
AIME 2026MathArena96.7%†–
HMMT February 2026MathArena89.4%†–
IMO 2025MathArena–16.7%†
MathArena ApexMathArena26.0%†–
Omni-MATH (HELM)HELM Capabilities–71.4%
MATH 500Vals AI–94.6%†
Arena MathsArena (LMArena)15041448
AIME 2025 (AA)Artificial Analysis–88.3%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub66.2%49.4%†
LiveBench 1.0 Data AnalysisLiveBench63.0%–
MMLU-ProVals AI89.3%85.6%†
LegalBenchVals AI86.7%83.8%†
CorpFinVals AI63.3%59.7%†
TaxEvalVals AI74.9%74.6%†
MedQAVals AI–96.1%†
PRBench FinanceScale AI SEAL–47.7%
PRBench LegalScale AI SEAL–48.6%
MultiNRCScale AI SEAL–45.5%†
MMLU-Pro (HELM)HELM Capabilities–85.9%
BioMysteryBenchVals AI58.5%–
Excel Modeling BenchmarkVals AI65.4%–
MedCodeVals AI53.1%47.3%†
MedScribeVals AI79.7%76.7%†
Public Benefits Bench v1.1Vals AI56.6%–
GDP.pdfEpoch AI Benchmarking Hub14.0%–
Instruction following
LiveBench LanguageLiveBench83.9%–
LiveBench Instruction FollowingLiveBench75.4%–
IFBenchArtificial Analysis–71.4%
MultiChallengeScale AI SEAL–56.6%†
TutorBenchScale AI SEAL–52.1%†
IFEval (HELM)HELM Capabilities–86.9%
WildBench (HELM)HELM Capabilities–86.1%
Arena Instruction FollowingArena (LMArena)14731403
Human preference
Arena TextArena (LMArena)14831432
Arena Creative WritingArena (LMArena)14711383
Arena Multi-turnArena (LMArena)14881420
Arena Longer QueriesArena (LMArena)14851411
Lech Mazur Creative WritingLech Mazur–83.9%†
Multimodal
Arena VisionArena (LMArena)12991214
MMMU-ProArtificial Analysis83.2%70.1%
VISTAScale AI SEAL–50.1%†
MMMU (validation)MMMU–82.9%
MMMU-Pro (official)MMMU–76.4%
MMMU-Pro (Vals)Vals AI88.4%80.4%†
MortgageTaxVals AI67.6%65.7%†
VTBScale AI SEAL–13.7%
GeoBenchGeoBench–60.0%†
VPCTEpoch AI Benchmarking Hub–52.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub31.2%†–
Long context
Fiction.LiveBench 120kFiction.live–100.0%†
AA-LCR v1.1Artificial Analysis80.0%74.7%
Arena DocumentArena (LMArena)1453–
MLCRArtificial Analysis10.0%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub154.7†146.9
LiveBench 1.0LiveBench73.6%–
AA Intelligence Index v4.3.2Artificial Analysis34.020.2
AA Progress Index v1Artificial Analysis305.7258.3
HELM Capabilities meanHELM Capabilities–81.1%
Vals Multimodal IndexVals AI65.1%–
Safety & honesty
FORTRESSScale AI SEAL–16.0%
MASKScale AI SEAL–84.5%†
PropensityBenchScale AI SEAL–10.5%

Data as of 2026-11-02. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261026-cb69502a12d9 (https://benchmarks.duellab.org/releases/gb2-20261026-cb69502a12d9/), 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): BenchLeader Index 61.8 → 61.2.
  • Gemini 3.6 Flash (high): 1 new result (AA Progress Index v1).
  • o3: 1 new result (AA Progress Index v1).
  • Gemini 3.6 Flash (high): 1 new result (Harvey's Legal Agent Benchmark v1).
  • Gemini 3.6 Flash (high): 1 score revision.
  • o3: 1 score revision.
  • Gemini 3.6 Flash (high): 3 new results (AutomationBench, GDP.pdf (AA), MLCR).
  • Gemini 3.6 Flash (high): BenchLeader Index 61.0 → 61.8.
  • Gemini 3.6 Flash (high): 1 score revision.

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

Gemini 3.6 Flash vs o3: questions

Is Gemini 3.6 Flash better than o3?
Gemini 3.6 Flash (high) and o3 are neck and neck on quality (61.3 vs 61.0, within the ±4.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2 Nov 2026, so check the category scores for your use.
Gemini 3.6 Flash vs o3: which is cheaper, and will that change?
Gemini 3.6 Flash is cheaper today: $1.50 against $3.50 per million tokens, blended at three input tokens per output token. Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.
Is Gemini 3.6 Flash or o3 better for coding?
o3 scores higher in coding (62 vs 57 on the category index, where 50 is average). On Arena Coding, the top shared coding benchmark, it is 1518 for Gemini 3.6 Flash against 1460 for o3.
Which is faster, Gemini 3.6 Flash or o3?
Gemini 3.6 Flash streams faster (197 vs 160 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.6 Flash or o3 better for agents and tool use?
o3 scores higher in agentic tasks (70 vs 59 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Gemini 3.6 Flash scores higher on long-context benchmarks (65 vs 62). Gemini 3.6 Flash accepts more context: 1,048,576 against 200,000 tokens for o3.
Which has lower latency?
o3 answers first: 6.8 s against 16.4 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 o3?
Across the 14 benchmarks both have, Gemini 3.6 Flash leads 14, o3 leads 0. Every overall index that rates both puts Gemini 3.6 Flash ahead.
When was Gemini 3.6 Flash released?
Gemini 3.6 Flash was released on 21 Jul 2026.