BenchLeader

Gemini 3.8 Flash vs o3

Full profiles: Gemini 3.8 Flash (Google) and o3 (OpenAI): every benchmark, price and rank.

Updated · Data from 17 sources

As of 16 Nov 2026, Gemini 3.8 Flash and o3 are neck and neck on quality (60.2 vs 60.4 on the BenchLeader Index, inside the ±5.9 margin), and Gemini 3.8 Flash is 2.3× cheaper at $1.50 vs $3.50 per 1M tokens blended. Choose Gemini 3.8 Flash for multimodal (67 vs 53), long context (67 vs 62), and agents & tools (75 vs 70); choose o3 for fast first answers (5.2 s vs 14.8 s) and coding (60 vs 52) and reasoning (61 vs 59). Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 16 Nov 2026)

  • Gemini 3.8 Flash scores 60.2 on the BenchLeader Index and o3 scores 60.4 (BenchLeader, 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).
  • o3 costs $3.50 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 6 benchmarks both models have, Gemini 3.8 Flash leads 6 (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
Codingo360 vs 52 category scoreHigh
Agents & tool useGemini 3.8 Flash75 vs 70 category scoreMedium
Reasoningo361 vs 59 category score; GPQA Diamond (AA) 82.7% vs 93.5%Medium
KnowledgeGemini 3.8 Flash58 vs 56 category scoreMedium
Long documentsGemini 3.8 Flash67 vs 62 category score; AA-LCR v1.1 84.0% vs 74.7%Medium
Images and other mediaGemini 3.8 Flash67 vs 53 category score; MMMU-Pro 84.2% vs 70.1%High
Chat quality (human preference)–Only o3 has an Arena rating (61 category score)Not comparable
Lowest costGemini 3.8 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 answero35.2 s (o3) 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 3.8 Flash (medium) and o3 are neck and neck on quality (60.2 vs 60.4, within the ±5.9 margin).
  • Gemini 3.8 Flash (medium) is stronger in agents & tools, knowledge, long context, multimodal.
  • o3 is stronger in coding, reasoning.
  • Gemini 3.8 Flash (medium) 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 3.8 Flasho3
DeveloperGoogleOpenAI
Released2 Sep 202616 Apr 2025
Context window (tokens)1,048,576200,000
Compared atGemini 3.8 Flash (medium)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 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 3.8 Flash (medium)o3Leader
Reasoning58.760.9o3
Coding51.659.8o3
Agents & tools75.070.3Gemini 3.8 Flash
Maths–70.6not comparable
Knowledge57.756.2Gemini 3.8 Flash
Instruction following–65.2not comparable
Human preference–61.0not comparable
Multimodal66.752.8Gemini 3.8 Flash
Long context66.761.9Gemini 3.8 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 & toolsKnowledgeLong contextMultimodalGemini 3.8 Flash, Reasoning: 58.7Gemini 3.8 Flash, Coding: 51.6Gemini 3.8 Flash, Agents & tools: 75.0Gemini 3.8 Flash, Knowledge: 57.7Gemini 3.8 Flash, Long context: 66.7Gemini 3.8 Flash, Multimodal: 66.7o3, Reasoning: 60.9o3, Coding: 59.8o3, Agents & tools: 70.3o3, Knowledge: 56.2o3, Long context: 61.9o3, Multimodal: 52.8

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

Model, click to add or removeIndex

Where sources disagree

Across the 6 benchmarks both have, Gemini 3.8 Flash leads 6, o3 leads 0. Every overall index that rates both puts Gemini 3.8 Flash ahead.

Overall indexGemini 3.8 Flash (medium)o3Leader
BenchLeader Index60.260.4neck and neck
Arena Text1497†1432Gemini 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 3.8 Flash (medium)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
Cost per benchmark task (AA Index)$6.26–
Output tokens per task (AA Index)82k–
Of which reasoning47k–
Time per task (AA Index)12 min–
Output speed116 tok/s131 tok/s
Time to first answer14.8 s5.2 s
Time to a complete answer, last measured 13 Nov 202641.8 s17.3 s

Each model is compared at its best-ranked reasoning-effort setting. 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. o3 scores 60.4 and takes 5 s to its first answer token; o3 (high) scores 55.1 in 5 s, o3 (medium) scores 53.3 in 5 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

221 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 3.8 Flash (medium)o3
BenchLeader IndexBenchLeader60.260.4
Agents & tools scoreBenchLeader75.070.3
Coding scoreBenchLeader51.659.8
Knowledge scoreBenchLeader57.756.2
Long context scoreBenchLeader66.761.9
Multimodal scoreBenchLeader66.752.8
Reasoning scoreBenchLeader58.760.9
Human preference scoreBenchLeader–61.0
Instruction following scoreBenchLeader–65.2
Maths scoreBenchLeader–70.6
Blended price $/MBenchLeader$1.50$3.50
Output speedBenchLeader116 tok/s131 tok/s
Time to first answerBenchLeader14.8 s5.2 s
Context windowBenchLeader1,048,576 tokens200,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub95.4%†81.8%†
Humanity's Last ExamScale AI / CAIS44.5%†20.3%†
SimpleBenchSimpleBench82.4%†53.1%†
Arena Hard PromptsArena (LMArena)1518†1441
LiveBench 2.0 ReasoningLiveBench89.3%†–
LiveBench 1.0 ReasoningLiveBench89.3%†–
GPQA Diamond (AA)Artificial Analysis93.5%82.7%
Humanity's Last Exam (AA)Artificial Analysis42.1%20.1%
HLE-Diamond (AA)Artificial Analysis29.1%–
GPQA Diamond (Vals)Vals AI94.4%†84.1%†
Kagi LLM BenchmarkKagi LLM Benchmark–67.6%
GPQA Diamond (HELM)HELM Capabilities–75.3%
ARC-AGI-1ARC Prize97.5%60.8%†
ARC-AGI-2ARC Prize82.9%6.5%†
ARC-AGI-3ARC Prize24.2%–
CritPtArtificial Analysis12.3%1.1%
CritPt v2 hard subset (AA)Artificial Analysis45.0%–
MysteryMechanismVals AI36.5%†–
SciPredictScale AI SEAL–17.9%
HLE-Diamond (Scale)Scale AI SEAL34.3%†–
Arena ExpertArena (LMArena)1527†1448
Chess PuzzlesEpoch AI Benchmarking Hub58.0%†36.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub47.0%†29.0%†
CL-benchEpoch AI Benchmarking Hub–17.8%†
LMCAEpoch AI Benchmarking Hub52.9%39.7%†
Show all 221 benchmarks
MetricPublisherGemini 3.8 Flash (medium)o3
Reasoning
DTBenchEpoch AI Benchmarking Hub94.9%84.8%†
ForecastBenchForecastBench–64.3%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–62.3%†
SciCodeSciCode55.1%–
WeirdMLWeirdML84.8%†52.4%†
FrontierCodeCognition41.2%–
GSO-BenchGSO-Bench–8.8%†
Arena CodingArena (LMArena)1531†1460
Arena WebDevArena (LMArena)1584†–
LiveBench 2.0 CodingLiveBench73.3%†–
LiveBench 1.0 CodingLiveBench72.5%†–
LiveCodeBenchVals AI89.5%†83.9%†
IOIVals AI56.9%†–
SWE-bench (Vals)Vals AI80.0%†–
Aider PolyglotAider polyglot leaderboard–76.9%
SWE-bench Verified (bash only)SWE-bench–58.4%
SWE-bench Verified (any scaffold)SWE-bench–58.4%
Code MigrationVals AI36.5%†–
Code Migration v1.1Vals AI38.6%†–
ProgramBenchVals AI1.0%†–
SWE-bench MultimodalVals AI40.8%†–
Vibe Code Bench 1-100Vals AI18.8%†–
Vibe Code Bench v1.1Vals AI78.7%†–
SWE Atlas v1.0: Codebase QnAScale AI SEAL47.0%†–
SWE Atlas v1.0: RefactoringScale AI SEAL44.8%†–
SWE Atlas v1.0: Test WritingScale AI SEAL53.7%†–
SWE Atlas v1.1Scale AI SEAL57.3%†–
SWE Atlas v1.1: Codebase QnAScale AI SEAL45.2%†–
SWE Atlas v1.1: Test WritingScale AI SEAL71.1%†–
SWE Atlas v1.1: RefactoringScale AI SEAL55.7%†–
SWE-Bench Pro V2Scale AI SEAL94.9%†–
SWE-Bench Pro V2 HARDScale AI SEAL58.8%†–
MirrorCodeEpoch AI Benchmarking Hub38.9%†–
CadEvalEpoch AI Benchmarking Hub–74.0%†
Surface Evolver BenchEpoch AI Benchmarking Hub76.9%†–
DeepSWE v1.1Epoch AI Benchmarking Hub71.0%–
CursorBenchCursor37.3%–
ALE-BenchEpoch AI Benchmarking Hub1269.7†933.5†
FrontierSWEEpoch AI Benchmarking Hub19.6%†–
WeirdML v3WeirdML7.4%†–
Terminal-Bench 4.0 (AA)Artificial Analysis19.7%–
Terminal-Bench 2.1 (AA)Artificial Analysis83.9%–
Startrise FrontendStartrise64.6%†–
GameBench 2 OverallDuelLab GameBench 259.0†34.1
GameBench 2 by reasoning settingDuelLab GameBench 259.730.4†
Design Arena WebsiteDesign Arena1291†1028
FrontierCode 1.1 (AA)Artificial Analysis37.1%–
FrontierCode 2.0 (AA)Artificial Analysis16.5%–
LiveCodeBench (AA)Artificial Analysis–80.8%
Agents & tools
Terminal-BenchTerminal-Bench18.2%†–
GDPvalOpenAI–30.8%†
Remote Labor IndexScale AI / CAIS5.8%†–
APEX-AgentsMercor64.3%†–
Arena AgentArena (LMArena)2.3†–
LiveBench Long AgenticLiveBench16.5%†–
LiveBench BrowserLiveBench45.1%†–
LiveBench Agentic CodingLiveBench54.2%†–
Terminal-Bench HardArtificial Analysis–37.1%
τ²-Bench Telecom (AA)Artificial Analysis–80.7%
Terminal-Bench 2.1 (Vals)Vals AI81.3%†–
HiL-BenchScale AI SEAL41.5%†–
BFCL OverallBerkeley Function Calling Leaderboard–63.0%
GDPval-AA v2.1, normalised scoreArtificial Analysis46.1%–
GDPval-AA v2.1Artificial Analysis1432–
τ³-Banking (AA)Artificial Analysis45.8%–
ITBench SRE (AA)Artificial Analysis52.5%†–
Analyst Agent (AA)Artificial Analysis46.3%†–
CUA-benchVals AI4.2%†–
CyberBenchVals AI43.8%†–
Finance Agent v2Vals AI61.4%†–
Finance Agent v2.1Vals AI65.8%†–
Harvey's Legal Agent Benchmark v1.1Vals AI12.1%†–
Harvey's Legal Agent Benchmark v1Vals AI10.0%†–
Legal Research BenchVals AI38.9%†–
SkillsBenchVals AI58.0%†–
SREBenchVals AI11.1%†–
Tax Agent BenchVals AI32.1%†–
Terminal-Bench 4.0 (Vals)Vals AI19.7%†–
Terminal-Bench ScienceVals AI8.6%†–
Time Horizon Index: KSPVals AI18.8%†–
Arena SearchArena (LMArena)–1197
Arena Agent Task CompletionArena (LMArena)1.3†–
DeepResearch BenchDeepResearch Bench–45.2%†
METR Time HorizonsMETR–63.6%
Vending-Bench 2Andon Labs5093.8†–
AutomationBenchArtificial Analysis60.9%–
GDP.pdf (AA)Artificial Analysis22.8%–
Harvey LAB-AA v1.1Harvey0.0%†–
AA-Briefcase v1.1Artificial Analysis1183–
Design Arena AgenticDesign Arena1225†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis10.5%–
CWE-Bench (AA)Artificial Analysis52.5%†–
DeepSec-Bench (AA)Artificial Analysis14.5%†–
CyberGym end-to-end (AA)Artificial Analysis8.4%†–
MKA (AA)Artificial Analysis35.3%†–
BrowseComp-PlusBrowseComp-Plus–50.5%
FACTS SearchGoogle80.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub68.4%†33.3%†
FrontierMath Tier 4Epoch AI Benchmarking Hub21.9%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub98.9%†83.9%†
MATH Level 5Epoch AI Benchmarking Hub–97.8%†
ProofBenchVals AI48.0%†–
LiveBench MathematicsLiveBench91.6%†–
AIME (Vals)Vals AI–85.3%†
MGSMVals AI–91.8%†
IMO 2025MathArena–16.7%†
Omni-MATH (HELM)HELM Capabilities–71.4%
MATH 500Vals AI–94.6%†
Arena MathsArena (LMArena)1519†1448
FrontierMath ErdősEpoch AI Benchmarking Hub0.0%†–
AIME 2025 (AA)Artificial Analysis–88.3%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub69.7%†49.4%†
LiveBench 2.0 Data AnalysisLiveBench54.0%†–
LiveBench ResearchLiveBench79.4%†–
LiveBench 1.0 Data AnalysisLiveBench54.0%†–
AA-Omniscience v1.1Artificial Analysis23.7–
MMLU-ProVals AI90.2%†85.6%†
LegalBenchVals AI87.0%†83.8%†
CorpFinVals AI–59.7%†
TaxEvalVals AI74.5%†74.6%†
MedQAVals AI–96.1%†
PRBench FinanceScale AI SEAL49.5%†47.7%
PRBench LegalScale AI SEAL48.9%†48.6%
MultiNRCScale AI SEAL–45.5%†
MMLU-Pro (HELM)HELM Capabilities–85.9%
BioMysteryBenchVals AI62.2%†–
Excel Modeling BenchmarkVals AI72.2%†–
Excel Modeling Benchmark v1.1Vals AI72.9%†–
MedCodeVals AI48.1%†47.3%†
MedScribeVals AI84.5%†76.7%†
Public Benefits Bench v1.1Vals AI65.3%†–
Access to Justice BenchmarkVals AI67.1%†–
Financial Coaching BenchVals AI66.3%†–
Immigration BenchVals AI63.4%†–
GDP.pdfEpoch AI Benchmarking Hub23.4%–
AA-Omniscience v1.1: accuracyArtificial Analysis49.6%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis48.5%–
HealthBench Professional (AA)OpenAI51.7%†–
FACTS ParametricGoogle78.7%†–
Instruction following
LiveBench LanguageLiveBench87.8%†–
LiveBench Instruction FollowingLiveBench81.4%†–
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)1492†1403
Human preference
Arena TextArena (LMArena)1497†1432
EQ-Bench Creative Writing v3EQ-Bench1744†1675
Arena Creative WritingArena (LMArena)1488†1383
Arena Multi-turnArena (LMArena)1505†1420
Arena Longer QueriesArena (LMArena)1511†1411
Lech Mazur Creative WritingLech Mazur–83.9%†
Multimodal
Arena VisionArena (LMArena)1317†1214
LiveBench DesignLiveBench69.7%†–
MMMU-ProArtificial Analysis84.2%70.1%
VISTAScale AI SEAL–50.1%†
MMMU-Pro (Vals)Vals AI89.1%†80.4%†
MortgageTaxVals AI65.3%†65.7%†
SAGEVals AI88.2%†–
AudioMCScale AI SEAL60.4%†–
AudioMC (text output)Scale AI SEAL60.4%†–
Humanity's Sixth SenseScale AI SEAL41.6%†–
VTBScale AI SEAL–13.7%
GeoBenchGeoBench86.0%†60.0%†
VPCTEpoch AI Benchmarking Hub–52.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub38.6%†–
Furniture AssemblyEpoch AI Benchmarking Hub31.7%†–
VIALS-AAHandshake AI41.0%†–
Code2Video-AAArtificial Analysis899†–
AA-3DArtificial Analysis974†–
FACTS MultimodalGoogle57.6%†–
Long context
Fiction.LiveBench 120kFiction.live–100.0%†
AA-LCR v1.1Artificial Analysis84.0%74.7%
Arena DocumentArena (LMArena)1469†–
MLCRArtificial Analysis12.8%–
FACTS GroundingGoogle68.2%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub158.8†147.1
LiveBench 2.0LiveBench57.3%†–
LiveBench 1.0LiveBench75.8%†–
AA Intelligence Index v5.0.1Artificial Analysis30.1–
AA Intelligence Index v4.3.2Artificial Analysis39.820.2
AA Progress Index v1Artificial Analysis319.1258.3
Vals IndexVals AI56.0†–
HELM Capabilities meanHELM Capabilities–81.1%
Vals Finance IndexVals AI60.5%†–
Vals RSI IndexVals AI19.9%†–
Vals Science IndexVals AI35.8%†–
Vals Router IndexVals AI56.0%†–
Vals Legal IndexVals AI69.8%†–
AA Cyber IndexArtificial Analysis25.1†–
Safety & honesty
FORTRESSScale AI SEAL–16.0%
MASKScale AI SEAL–84.5%†
PropensityBenchScale AI SEAL–10.5%
DistressBenchScale AI SEAL70.7%†–
Metadata
AA Openness IndexArtificial Analysis–5.6

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).
  • o3: BenchLeader Index 61.2 → 60.4.
  • o3: 1 score revision.
  • Gemini 3.8 Flash (medium): 1 score revision.
  • o3: 1 new result (Arena Search).
  • Gemini 3.8 Flash (medium): 2 score revisions.
  • o3: 1 score revision.
  • 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.

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

Gemini 3.8 Flash vs o3: questions

Is Gemini 3.8 Flash better than o3?
Gemini 3.8 Flash (medium) and o3 are neck and neck on quality (60.2 vs 60.4, within the ±5.9 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 3.8 Flash vs o3: which is cheaper, and will that change?
Gemini 3.8 Flash is cheaper today: $1.50 against $3.50 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 3.8 Flash or o3 better for coding?
o3 scores higher in coding (60 vs 52 on the category index, where 50 is average).
Which is faster, Gemini 3.8 Flash or o3?
o3 streams faster (131 vs 116 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.8 Flash or o3 better for agents and tool use?
Gemini 3.8 Flash scores higher in agentic tasks (75 vs 70 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Gemini 3.8 Flash scores higher on long-context benchmarks (67 vs 62). Gemini 3.8 Flash accepts more context: 1,048,576 against 200,000 tokens for o3.
Which has lower latency?
o3 answers first: 5.2 s against 14.8 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 3.8 Flash vs o3?
Across the 6 benchmarks both have, Gemini 3.8 Flash leads 6, o3 leads 0. 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.