BenchLeader
Menu

Gemini 3.5 Flash vs Gemini 4 Hydrogen

Full profiles: Gemini 3.5 Flash (Google) and Gemini 4 Hydrogen (Google): every benchmark, price and rank.

Updated · Data from 12 sources

As of 13 Nov 2026, Gemini 3.5 Flash and Gemini 4 Hydrogen are neck and neck on quality (62.5 vs 63.4 on the BenchLeader Index, inside the ±3.3 margin), and they cost about the same at $3.38 vs $3.00 per 1M tokens blended. Choose 3.5 Flash for agents & tools (63 vs 62); choose 4 Hydrogen for maths (68 vs 58), coding (69 vs 60), and reasoning (70 vs 61).

Key facts (as of 13 Nov 2026)

  • Gemini 3.5 Flash scores 62.5 on the BenchLeader Index and Gemini 4 Hydrogen scores 63.4 (BenchLeader, 13 Nov 2026).
  • Gemini 3.5 Flash costs $3.38 per 1M tokens blended (list price, 13 Nov 2026).
  • Gemini 4 Hydrogen costs $3.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Of the 12 benchmarks both models have, Gemini 4 Hydrogen leads 10 (BenchLeader, 13 Nov 2026).
  • On Arena WebDev, Gemini 3.5 Flash is rated 1500 and Gemini 4 Hydrogen 1704 (LMArena, as published by 13 Nov 2026).
Gemini 3.5 Flash benchmarks high Google Gemini 4 Hydrogen benchmarks high GoogleAdd 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
CodingGemini 4 Hydrogen69 vs 60 category score; Arena WebDev 1704 vs 1500High
Agents & tool useGemini 3.5 Flash63 vs 62 category score; AutomationBench 42.1% vs 74.4%Medium
MathsGemini 4 Hydrogen68 vs 58 category score; Arena Maths 1495 vs 1497High
ReasoningGemini 4 Hydrogen70 vs 61 category score; Arena Hard Prompts 1514 vs 1496High
KnowledgeGemini 4 Hydrogen69 vs 63 category scoreMedium
Chat quality (human preference)Gemini 4 Hydrogen68 vs 67 on Arena votesMedium
Lowest costEither$3.38 vs $3.00 per 1M blended; agentic coding session $0.126 vs $0.120–
Fastest first answerGemini 3.5 Flash12.4 s (Gemini 3.5 Flash (high)) vs 16.4 s (Gemini 4 Hydrogen (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 3.5 Flash (high) and Gemini 4 Hydrogen (high) are neck and neck on quality (62.5 vs 63.4, within the ±3.3 margin).
  • Gemini 3.5 Flash (high) is stronger in agents & tools.
  • Gemini 4 Hydrogen (high) is stronger in coding, human preference, knowledge, maths, reasoning.
  • They cost about the same ($3.00 per 1M blended).

At a glance

SpecGemini 3.5 FlashGemini 4 Hydrogen
DeveloperGoogleGoogle
Released19 May 202612 Nov 2026
Context window (tokens)1,048,5761,048,576
Compared atGemini 3.5 Flash (high)Gemini 4 Hydrogen (high)
Open weightsNoNo
Price in / out / cached input per 1M$1.50 / $9.00 / $0.150$1.50 / $7.50 / $0.075

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 3.5 Flash (high)Gemini 4 Hydrogen (high)Leader
Reasoning60.569.6Gemini 4 Hydrogen
Coding59.568.8Gemini 4 Hydrogen
Agents & tools62.961.9Gemini 3.5 Flash
Maths57.967.8Gemini 4 Hydrogen
Knowledge63.368.5Gemini 4 Hydrogen
Instruction following74.4–not comparable
Human preference66.868.2Gemini 4 Hydrogen
Multimodal66.2–not comparable
Long context61.2–not 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 & toolsMathsKnowledgeHumanpreferenceGemini 3.5 Flash, Reasoning: 60.5Gemini 3.5 Flash, Coding: 59.5Gemini 3.5 Flash, Agents & tools: 62.9Gemini 3.5 Flash, Maths: 57.9Gemini 3.5 Flash, Knowledge: 63.3Gemini 3.5 Flash, Human preference: 66.8Gemini 4 Hydrogen, Reasoning: 69.6Gemini 4 Hydrogen, Coding: 68.8Gemini 4 Hydrogen, Agents & tools: 61.9Gemini 4 Hydrogen, Maths: 67.8Gemini 4 Hydrogen, Knowledge: 68.5Gemini 4 Hydrogen, Human preference: 68.2

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

Model, click to add or removeIndex

Where sources disagree

Across the 12 benchmarks both have, Gemini 3.5 Flash leads 2, Gemini 4 Hydrogen leads 10. Every overall index that rates both puts Gemini 4 Hydrogen ahead.

Overall indexGemini 3.5 Flash (high)Gemini 4 Hydrogen (high)Leader
BenchLeader Index62.563.4neck and neck
Arena Text14781490Gemini 4 Hydrogen

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 3.5 Flash (high)Gemini 4 Hydrogen (high)
Blended price per 1M tokens$3.38$3.00
Input / output per 1M$1.50 / $9.00$1.50 / $7.50
Cached input per 1M$0.150$0.075
Price per task: chat reply$0.0033$0.0029
Price per task: summarize a 30-page report$0.023$0.022
Price per task: code edit$0.022$0.020
Price per task: agentic coding session$0.126$0.120
Price per task: structured extraction$0.0048$0.0045
Agentic coding session, input mostly cached$0.065$0.056
Cost per benchmark task (AA Index)–$1.87
Output tokens per task (AA Index)–85k
Of which reasoning–48k
Time per task (AA Index)–8 min
Output speed167 tok/s180 tok/s
Time to first answer12.4 s16.4 s
Time to a complete answer27.6 s63.3 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.5 Flash (high) scores 62.5 and takes 12 s to its first answer token; Gemini 3.5 Flash (medium) scores 61.8 in 11 s, Gemini 3.5 Flash (minimal) scores 55.6 in 3 s. Gemini 4 Hydrogen (high) scores 63.4 and takes 16 s to its first answer token. 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

129 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 3.5 Flash (high)Gemini 4 Hydrogen (high)
BenchLeader IndexBenchLeader62.563.4
Agents & tools scoreBenchLeader62.961.9
Coding scoreBenchLeader59.568.8
Human preference scoreBenchLeader66.868.2
Instruction following scoreBenchLeader74.4–
Knowledge scoreBenchLeader63.368.5
Long context scoreBenchLeader61.2–
Maths scoreBenchLeader57.967.8
Multimodal scoreBenchLeader66.2–
Reasoning scoreBenchLeader60.569.6
Blended price $/MBenchLeader$3.38$3.00
Output speedBenchLeader167 tok/s180 tok/s
Time to first answerBenchLeader12.4 s16.4 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub92.8%–
SimpleBenchSimpleBench76.7%†–
Arena Hard PromptsArena (LMArena)14961514
LiveBench 2.0 ReasoningLiveBench–88.6%†
LiveBench 1.0 ReasoningLiveBench82.0%–
GPQA Diamond (AA)Artificial Analysis92.2%–
Humanity's Last Exam (AA)Artificial Analysis42.7%–
HLE-Diamond (AA)Artificial Analysis–54.9%
GPQA Diamond (Vals)Vals AI92.7%–
EnigmaEvalScale AI SEAL25.4%–
ARC-AGI-1ARC Prize92.5%–
ARC-AGI-2ARC Prize72.1%–
CritPtArtificial Analysis13.1%–
CritPt v2 hard subset (AA)Artificial Analysis–61.5%
Chess PuzzlesEpoch AI Benchmarking Hub45.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub32.0%–
LMCAEpoch AI Benchmarking Hub47.1%–
DTBenchEpoch AI Benchmarking Hub94.7%–
ForecastBenchForecastBench64.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub79.3%–
SciCodeSciCode53.9%–
WeirdMLWeirdML62.6%–
Arena CodingArena (LMArena)15081518
Arena WebDevArena (LMArena)15001704
LiveBench 2.0 CodingLiveBench–78.5%†
Show all 129 benchmarks
MetricPublisherGemini 3.5 Flash (high)Gemini 4 Hydrogen (high)
Coding
LiveBench 1.0 CodingLiveBench78.2%–
LiveCodeBenchVals AI87.6%–
SWE-bench (Vals)Vals AI78.8%–
Code MigrationVals AI26.8%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI48.7%87.8%†
Surface Evolver BenchEpoch AI Benchmarking Hub58.1%†–
DeepSWE v1.1Epoch AI Benchmarking Hub36.1%–
ALE-BenchEpoch AI Benchmarking Hub911.0–
Terminal-Bench 4.0 (AA)Artificial Analysis6.6%54.0%
Terminal-Bench 2.1 (AA)Artificial Analysis78.7%–
GameBench 2 OverallDuelLab GameBench 249.3†–
GameBench 2 by reasoning settingDuelLab GameBench 262.2–
Design Arena WebsiteDesign Arena1259†1316†
FrontierCode 2.0 (AA)Artificial Analysis–36.3%
Agents & tools
Terminal-BenchTerminal-Bench–56.4%
APEX-AgentsMercor27.5%†–
LiveBench Long AgenticLiveBench–61.8%†
LiveBench BrowserLiveBench–77.1%†
LiveBench Agentic CodingLiveBench49.0%–
Terminal-Bench HardArtificial Analysis40.9%–
τ²-Bench Telecom (AA)Artificial Analysis95.3%–
Terminal-Bench 2.1 (Vals)Vals AI74.2%–
MCP AtlasScale AI SEAL83.6%–
HiL-BenchScale AI SEAL27.7%†–
τ³-Banking (AA)Artificial Analysis32.2%–
ITBench SRE (AA)Artificial Analysis40.4%–
Analyst Agent (AA)Artificial Analysis45.0%–
APEX-Agents (AA)Artificial Analysis47.0%–
Finance Agent v2Vals AI57.9%–
Finance Agent v2.1Vals AI–65.1%†
Harvey's Legal Agent Benchmark v1.1Vals AI–11.3%†
Harvey's Legal Agent Benchmark v1Vals AI2.5%–
Legal Research BenchVals AI30.8%53.9%†
SkillsBenchVals AI52.7%–
Tax Agent BenchVals AI21.6%52.3%†
Terminal-Bench 2.0 (Vals)Vals AI67.4%–
Terminal-Bench 4.0 (Vals)Vals AI6.1%54.0%†
Terminal-Bench ScienceVals AI5.7%–
Web Search IndexVals AI37.0%–
GBAEvalEpoch AI Benchmarking Hub6.7%†–
Vending-Bench 2Andon Labs5396.4†–
AutomationBenchArtificial Analysis42.1%74.4%
GDP.pdf (AA)Artificial Analysis19.8%30.0%
EnterpriseOps-GymArtificial Analysis50.1%–
AA-Briefcase v1.1Artificial Analysis8761497
Design Arena AgenticDesign Arena1166†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–41.4%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub62.8%–
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%–
OTIS Mock AIMEEpoch AI Benchmarking Hub95.6%–
ProofBenchVals AI31.0%–
LiveBench MathematicsLiveBench88.2%–
AIME 2026MathArena95.0%–
HMMT February 2026MathArena95.5%–
MathArena ApexMathArena32.3%–
Arena MathsArena (LMArena)14971495
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub66.2%–
LiveBench 2.0 Data AnalysisLiveBench–83.2%†
LiveBench ResearchLiveBench–86.8%†
LiveBench 1.0 Data AnalysisLiveBench64.9%–
AA-Omniscience v1.1Artificial Analysis–43.7
MMLU-ProVals AI89.5%–
LegalBenchVals AI83.6%–
CorpFinVals AI64.7%–
TaxEvalVals AI74.4%–
Excel Modeling BenchmarkVals AI63.5%–
Excel Modeling Benchmark v1.1Vals AI–75.8%†
MedCodeVals AI55.8%–
MedScribeVals AI76.6%–
Public Benefits Bench v1.1Vals AI59.5%–
DrugDiscoveryBenchScale AI SEAL50.0%–
EBR-benchEpoch AI Benchmarking Hub4.8%–
GDP.pdfEpoch AI Benchmarking Hub14.0%†–
AA-Omniscience v1.1: accuracyArtificial Analysis–48.2%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–91.3%
Instruction following
LiveBench LanguageLiveBench84.6%–
LiveBench Instruction FollowingLiveBench75.6%–
IFBenchArtificial Analysis76.3%–
Arena Instruction FollowingArena (LMArena)14651503
Human preference
Arena TextArena (LMArena)14781490
EQ-Bench 4EQ-Bench1077†–
Arena Creative WritingArena (LMArena)14651492
Arena Multi-turnArena (LMArena)14801476
Arena Longer QueriesArena (LMArena)14831514
Multimodal
Arena VisionArena (LMArena)1308–
LiveBench DesignLiveBench–77.3%†
MMMU-ProArtificial Analysis84.3%–
MMMU-Pro (Vals)Vals AI88.3%–
MortgageTaxVals AI68.1%–
GeoBenchGeoBench85.0%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub33.6%†–
Long context
AA-LCR v1.1Artificial Analysis73.3%–
Arena DocumentArena (LMArena)1455–
MLCRArtificial Analysis10.0%21.1%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub155.3†–
LiveBench 2.0LiveBench–77.0%†
LiveBench 1.0LiveBench74.6%–
AA Intelligence Index v5.0Artificial Analysis–50.8
AA Intelligence Index v4.3.2Artificial Analysis32.6–
AA Progress Index v1Artificial Analysis305.1–
Vals IndexVals AI–68.5†
Vals Finance IndexVals AI–66.1%†
Vals Multimodal IndexVals AI62.9%–

Data as of 2026-11-13. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 4 Hydrogen (high): 10 new results (Arena Text, Arena Hard Prompts, Arena Coding…).
  • Gemini 3.5 Flash (high): 3 new results (AIME 2026, HMMT February 2026, MathArena Apex).
  • Gemini 3.5 Flash (high): 1 score revision.
  • Gemini 3.5 Flash (high): BenchLeader Index 63.2 → 62.6.
  • Gemini 3.5 Flash (high): 1 new result (AA Progress Index v1).
  • Gemini 3.5 Flash (high): cost per task moved from $3.69/M to $2.98/M (19% down).
  • Gemini 3.5 Flash (high): 1 new result (Harvey's Legal Agent Benchmark v1).
  • Gemini 3.5 Flash (high): 1 score revision.
  • Gemini 3.5 Flash (high): 3 new results (GDPval-AA v2.1, normalised score, AA-Omniscience v1.1: accuracy, AA-Omniscience v1.1: non-hallucination).
  • Gemini 3.5 Flash (high): 1 score revision.

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

Gemini 3.5 Flash vs Gemini 4 Hydrogen: questions

Is Gemini 3.5 Flash better than Gemini 4 Hydrogen?
Gemini 3.5 Flash (high) and Gemini 4 Hydrogen (high) are neck and neck on quality (62.5 vs 63.4, within the ±3.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 13 Nov 2026, so check the category scores for your use.
Gemini 3.5 Flash vs Gemini 4 Hydrogen: which is cheaper, and will that change?
Gemini 4 Hydrogen is cheaper today: $3.00 against $3.38 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemini 3.5 Flash or Gemini 4 Hydrogen better for coding?
Gemini 4 Hydrogen scores higher in coding (69 vs 60 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1500 for Gemini 3.5 Flash against 1704 for Gemini 4 Hydrogen.
Which is faster, Gemini 3.5 Flash or Gemini 4 Hydrogen?
Gemini 4 Hydrogen streams faster (180 vs 167 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.5 Flash or Gemini 4 Hydrogen better for agents and tool use?
Gemini 3.5 Flash scores higher in agentic tasks (63 vs 62 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 3.5 Flash answers first: 12.4 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 3.5 Flash vs Gemini 4 Hydrogen?
Across the 12 benchmarks both have, Gemini 3.5 Flash leads 2, Gemini 4 Hydrogen leads 10. Every overall index that rates both puts Gemini 4 Hydrogen ahead.
When was Gemini 4 Hydrogen released?
Gemini 4 Hydrogen was released on 12 Nov 2026.