BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases8

Gemini 3.5 Flash vs Gemini 4 Carbon

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

Updated · Data from 9 sources

As of 29 Oct 2026, Gemini 3.5 Flash and Gemini 4 Carbon are neck and neck on quality (62.6 vs 65.1 on the BenchLeader Index, inside the ±6.8 margin), and Gemini 3.5 Flash is 2.4× cheaper at $3.38 vs $8.00 per 1M tokens blended. Gemini 4 Carbon leads in every category we measure both in. Gemini 3.5 Flash streams ~2× faster.

Key facts (as of 29 Oct 2026)

  • Gemini 3.5 Flash scores 62.6 on the BenchLeader Index and Gemini 4 Carbon scores 65.1 (BenchLeader, 29 Oct 2026).
  • Gemini 3.5 Flash costs $3.38 per 1M tokens blended (list price, 29 Oct 2026).
  • Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 29 Oct 2026).
  • Gemini 3.5 Flash streams ~2× faster than Gemini 4 Carbon (Artificial Analysis, 7-day median, 29 Oct 2026).
  • Of the 13 benchmarks both models have, Gemini 4 Carbon leads 13 (BenchLeader, 29 Oct 2026).
Gemini 3.5 Flash benchmarks high Google Gemini 4 Carbon benchmarks high GoogleOpen in the comparison tool

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 Carbon72 vs 60 category score; SciCode 64.2% vs 53.9%High
ReasoningGemini 4 Carbon79 vs 61 category score; Humanity's Last Exam (AA) 60.4% vs 42.7%High
KnowledgeGemini 4 Carbon76 vs 63 category scoreHigh
Long documentsGemini 4 Carbon65 vs 61 category score; AA-LCR v1.1 79.3% vs 73.3%Medium
Chat quality (human preference)–Only Gemini 3.5 Flash has an Arena rating (67 category score)Not comparable
Lowest costGemini 3.5 Flash$3.38 vs $8.00 per 1M blended; agentic coding session $0.126 vs $0.320–
Fastest first answerGemini 3.5 Flash14.8 s (Gemini 3.5 Flash (high)) vs 103.1 s (Gemini 4 Carbon (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 Carbon (high) are neck and neck on quality (62.6 vs 65.1, within the ±6.8 margin).
  • Gemini 3.5 Flash (high) is stronger in agents & tools, human preference, instruction following, maths, multimodal.
  • Gemini 4 Carbon (high) is stronger in coding, knowledge, long context, reasoning.
  • Gemini 3.5 Flash (high) is 2.4× cheaper ($3.38 vs $8.00 per 1M blended).
  • Gemini 3.5 Flash (high) streams 2.2× faster (215 vs 100 tokens per second).

At a glance

SpecGemini 3.5 FlashGemini 4 Carbon
DeveloperGoogleGoogle
Released19 May 202628 Oct 2026
Context window (tokens)1,048,5761,000,000
Compared atGemini 3.5 Flash (high)Gemini 4 Carbon (high)
Open weightsNoNo
Price in / out / cached input per 1M$1.50 / $9.00 / $0.150$4.00 / $20.00 / –

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 Carbon (high)Leader
Reasoning61.078.9Gemini 4 Carbon
Coding59.771.7Gemini 4 Carbon
Agents & tools63.4–not comparable
Maths58.2–not comparable
Knowledge63.475.8Gemini 4 Carbon
Instruction following74.3–not comparable
Human preference66.8–not comparable
Multimodal66.4–not comparable
Long context61.464.5Gemini 4 Carbon

Where sources disagree

Across the 13 benchmarks both have, Gemini 3.5 Flash leads 0, Gemini 4 Carbon leads 13.

Overall indexGemini 3.5 Flash (high)Gemini 4 Carbon (high)Leader
BenchLeader Index62.665.1neck and neck

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; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

MeasureGemini 3.5 Flash (high)Gemini 4 Carbon (high)
Blended price per 1M tokens$3.38$8.00
Input / output per 1M$1.50 / $9.00$4.00 / $20.00
Cached input per 1M$0.150–
Price per task: chat reply$0.0033$0.0076
Price per task: summarize a 30-page report$0.023$0.060
Price per task: code edit$0.022$0.054
Price per task: agentic coding session$0.126$0.320
Price per task: structured extraction$0.0048$0.012
Cost to run a full benchmark suite–$7.76
Output speed215 tok/s100 tok/s
Time to first answer14.8 s103.1 s
Time to a complete answer17.1 s108.1 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.5 Flash (high) scores 62.6 and takes 15 s to its first answer token; Gemini 3.5 Flash (medium) scores 61.9 in 12 s, Gemini 3.5 Flash (minimal) scores 55.7 in 1 s. Gemini 4 Carbon (high) scores 65.1 and takes 103 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

117 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 Carbon (high)
BenchLeader IndexBenchLeader62.665.1
Agents & tools scoreBenchLeader63.4–
Coding scoreBenchLeader59.771.7
Human preference scoreBenchLeader66.8–
Instruction following scoreBenchLeader74.3–
Knowledge scoreBenchLeader63.475.8
Long context scoreBenchLeader61.464.5
Maths scoreBenchLeader58.2–
Multimodal scoreBenchLeader66.4–
Reasoning scoreBenchLeader61.078.9
Blended price $/MBenchLeader$3.38$8.00
Output speedBenchLeader215 tok/s100 tok/s
Time to first answerBenchLeader14.8 s103.1 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub92.8%–
SimpleBenchSimpleBench76.7%†–
Arena Hard PromptsArena (LMArena)1495–
LiveBench 1.0 ReasoningLiveBench82.0%–
GPQA Diamond (AA)Artificial Analysis92.2%–
Humanity's Last Exam (AA)Artificial Analysis42.7%60.4%
HLE-Diamond (AA)Artificial Analysis–69.1%
GPQA Diamond (Vals)Vals AI92.7%–
EnigmaEvalScale AI SEAL25.4%–
ARC-AGI-1ARC Prize92.5%–
ARC-AGI-2ARC Prize72.1%–
CritPtArtificial Analysis13.1%36.0%
CritPt v2 hard subset (AA)Artificial Analysis–63.0%
Chess PuzzlesEpoch AI Benchmarking Hub45.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub32.0%–
LMCAEpoch AI Benchmarking Hub47.1%–
DTBenchEpoch AI Benchmarking Hub94.7%–
ForecastBenchForecastBench64.4%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub79.3%–
SciCodeSciCode53.9%64.2%
WeirdMLWeirdML62.6%–
Arena CodingArena (LMArena)1508–
Arena WebDevArena (LMArena)1499–
LiveBench 1.0 CodingLiveBench78.2%–
LiveCodeBenchVals AI87.6%–
Show all 117 benchmarks
MetricPublisherGemini 3.5 Flash (high)Gemini 4 Carbon (high)
Coding
SWE-bench (Vals)Vals AI78.8%–
Code MigrationVals AI26.8%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI48.7%89.1%
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%65.2%
Terminal-Bench 2.1 (AA)Artificial Analysis78.7%–
FrontierCode 1.1 (AA)Artificial Analysis–48.5%
FrontierCode 2.0 (AA)Artificial Analysis–40.6%
Agents & tools
APEX-AgentsMercor27.5%†–
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–67.2%
Harvey's Legal Agent Benchmark v1.1Vals AI–17.5%
Harvey's Legal Agent Benchmark v1Vals AI2.5%–
Legal Research BenchVals AI30.8%55.8%
SkillsBenchVals AI52.7%–
Tax Agent BenchVals AI21.6%48.9%
Terminal-Bench 2.0 (Vals)Vals AI67.4%–
Terminal-Bench 4.0 (Vals)Vals AI6.1%63.1%
Terminal-Bench ScienceVals AI5.7%–
Web Search IndexVals AI37.0%–
GBAEvalEpoch AI Benchmarking Hub6.7%†–
Vending-Bench 2Andon Labs5396.4†16484.2†
AutomationBenchArtificial Analysis42.1%77.8%
GDP.pdf (AA)Artificial Analysis19.8%28.4%
EnterpriseOps-GymArtificial Analysis50.1%–
AA-Briefcase v1.1Artificial Analysis8751609
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–64.8%
FACTS SearchGoogle64.3%†–
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)1497–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub66.2%–
LiveBench 1.0 Data AnalysisLiveBench64.9%–
AA-Omniscience v1.1Artificial Analysis–53.5
MMLU-ProVals AI89.5%–
LegalBenchVals AI83.6%–
CorpFinVals AI64.7%–
TaxEvalVals AI74.4%–
Excel Modeling BenchmarkVals AI63.5%–
Excel Modeling Benchmark v1.1Vals AI–76.5%
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–58.3%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–88.6%
Instruction following
LiveBench LanguageLiveBench84.6%–
LiveBench Instruction FollowingLiveBench75.6%–
IFBenchArtificial Analysis76.3%–
Arena Instruction FollowingArena (LMArena)1465–
Human preference
Arena TextArena (LMArena)1477–
EQ-Bench 4EQ-Bench1077†–
Arena Creative WritingArena (LMArena)1464–
Arena Multi-turnArena (LMArena)1480–
Arena Longer QueriesArena (LMArena)1482–
Multimodal
Arena VisionArena (LMArena)1308–
MMMU-ProArtificial Analysis84.3%–
MMMU-Pro (Vals)Vals AI88.3%–
MortgageTaxVals AI68.1%–
Blueprint-Bench 2Epoch AI Benchmarking Hub33.6%†58.6%†
Long context
AA-LCR v1.1Artificial Analysis73.3%79.3%
Arena DocumentArena (LMArena)1453–
MLCRArtificial Analysis10.0%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub154.9†–
LiveBench 1.0LiveBench74.6%–
AA Intelligence Index v5.0Artificial Analysis–59.4
AA Intelligence Index v4.3.2Artificial Analysis32.6–
AA Progress Index v1Artificial Analysis305.1351.6
Vals IndexVals AI–70.4
Vals Finance IndexVals AI–66.3%
Vals Multimodal IndexVals AI62.9%–

Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.

What changed

  • 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): BenchLeader Index 63.4 → 62.9.
  • Gemini 3.5 Flash (high): 3 new results (GDPval-AA v2.1, AA-Omniscience v1.1: accuracy, AA-Omniscience v1.1: non-hallucination).
  • Gemini 3.5 Flash (high): 1 score revision.
  • Gemini 3.5 Flash (high): 2 score revisions.
  • Gemini 3.5 Flash (high): 1 new result (DrugDiscoveryBench).
  • Gemini 3.5 Flash (high): 1 new result (EnigmaEval).

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

Gemini 3.5 Flash vs Gemini 4 Carbon: questions

Is Gemini 3.5 Flash better than Gemini 4 Carbon?
Gemini 3.5 Flash (high) and Gemini 4 Carbon (high) are neck and neck on quality (62.6 vs 65.1, within the ±6.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 29 Oct 2026, so check the category scores for your use.
Gemini 3.5 Flash vs Gemini 4 Carbon: which is cheaper, and will that change?
Gemini 3.5 Flash is cheaper today: $3.38 against $8.00 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 Carbon better for coding?
Gemini 4 Carbon scores higher in coding (72 vs 60 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 53.9% for Gemini 3.5 Flash against 64.2% for Gemini 4 Carbon.
Which is faster, Gemini 3.5 Flash or Gemini 4 Carbon?
Gemini 3.5 Flash streams ~2× faster (215 vs 100 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Gemini 4 Carbon scores higher on long-context benchmarks (65 vs 61). Both take about 1M tokens: Gemini 3.5 Flash 1,048,576, Gemini 4 Carbon 1,000,000.
More questions (3)
Which has lower latency?
Gemini 3.5 Flash answers first: 14.8 s against 103.1 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 Carbon?
Across the 13 benchmarks both have, Gemini 3.5 Flash leads 0, Gemini 4 Carbon leads 13.
When was Gemini 4 Carbon released?
Gemini 4 Carbon was released on 28 Oct 2026.