BenchLeader

Gemini 3.5 Flash vs GLM 5.3 Flash

Full profiles: Gemini 3.5 Flash (Google) and GLM 5.3 Flash (Zhipu AI): every benchmark, price and rank.

Updated · Data from 13 sources

As of 16 Nov 2026, Gemini 3.5 Flash is ahead of GLM 5.3 Flash on quality (62.5 vs 57.8 on the BenchLeader Index), but GLM 5.3 Flash is 14× cheaper at $0.238 vs $3.38 per 1M tokens blended. Choose Gemini 3.5 Flash for knowledge (63 vs 45), reasoning (61 vs 48), and agents & tools (63 vs 59) and fast first answers (9.9 s vs 87.0 s), where it also streams 3×+ faster; choose GLM 5.3 Flash for maths (69 vs 58) and long context (65 vs 61).

Key facts (as of 16 Nov 2026)

  • Gemini 3.5 Flash scores 62.5 on the BenchLeader Index and GLM 5.3 Flash scores 57.8 (BenchLeader, 16 Nov 2026).
  • Gemini 3.5 Flash costs $3.38 per 1M tokens blended (list price, 16 Nov 2026).
  • GLM 5.3 Flash costs $0.238 per 1M tokens blended (list price, 16 Nov 2026).
  • Gemini 3.5 Flash streams 3×+ faster than GLM 5.3 Flash (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 35 benchmarks both models have, GLM 5.3 Flash leads 20 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Gemini 3.5 Flash is rated 1500 and GLM 5.3 Flash 1609 (LMArena, as published by 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 3.5 Flash60 vs 57 category score; SciCode 53.9% vs 51.6%Medium
Agents & tool useGemini 3.5 Flash63 vs 59 category score; τ³-Banking (AA) 32.2% vs 47.2%Medium
MathsGLM 5.3 Flash69 vs 58 category score; Arena Maths 1505 vs 1497High
ReasoningGemini 3.5 Flash61 vs 48 category score; Arena Hard Prompts 1496 vs 1500High
KnowledgeGemini 3.5 Flash63 vs 45 category score; LiveBench 1.0 Data Analysis 64.9% vs 76.4%High
Long documentsGLM 5.3 Flash65 vs 61 category score; AA-LCR v1.1 80.0% vs 73.3%Medium
Images and other mediaGemini 3.5 Flash66 vs 64 category score; Arena Vision 1308 vs 1295Medium
Chat quality (human preference)Either67 vs 66 on Arena votesEither
Lowest costGLM 5.3 Flash$0.238 vs $3.38 per 1M blended; agentic coding session $0.011 vs $0.126–
Fastest first answerGemini 3.5 Flash9.9 s (Gemini 3.5 Flash (high)) vs 87.0 s (GLM 5.3 Flash) 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) leads on quality: 62.5 vs 57.8.
  • Gemini 3.5 Flash (high) is stronger in agents & tools, coding, human preference, knowledge, multimodal, reasoning.
  • GLM 5.3 Flash is stronger in long context, maths.
  • GLM 5.3 Flash is 14× cheaper ($0.238 vs $3.38 per 1M blended).
  • Gemini 3.5 Flash (high) streams 3.2× faster (176 vs 54 tokens per second).

At a glance

SpecGemini 3.5 FlashGLM 5.3 Flash
DeveloperGoogleZhipu AI
Released19 May 202620 Aug 2026
Context window (tokens)1,048,5761,000,000
Compared atGemini 3.5 Flash (high)GLM 5.3 Flash
Open weightsNoYes
Price in / out / cached input per 1M$1.50 / $9.00 / $0.150$0.150 / $0.500 / $0.030

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)GLM 5.3 FlashLeader
Reasoning60.648.3Gemini 3.5 Flash
Coding59.556.9Gemini 3.5 Flash
Agents & tools62.858.7Gemini 3.5 Flash
Maths57.768.8GLM 5.3 Flash
Knowledge63.345.1Gemini 3.5 Flash
Instruction following74.4–not comparable
Human preference66.866.4level
Multimodal66.264.0Gemini 3.5 Flash
Long context61.264.6GLM 5.3 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 3.5 Flash, Reasoning: 60.6Gemini 3.5 Flash, Coding: 59.5Gemini 3.5 Flash, Agents & tools: 62.8Gemini 3.5 Flash, Maths: 57.7Gemini 3.5 Flash, Knowledge: 63.3Gemini 3.5 Flash, Long context: 61.2Gemini 3.5 Flash, Multimodal: 66.2Gemini 3.5 Flash, Human preference: 66.8GLM 5.3 Flash, Reasoning: 48.3GLM 5.3 Flash, Coding: 56.9GLM 5.3 Flash, Agents & tools: 58.7GLM 5.3 Flash, Maths: 68.8GLM 5.3 Flash, Knowledge: 45.1GLM 5.3 Flash, Long context: 64.6GLM 5.3 Flash, Multimodal: 64.0GLM 5.3 Flash, Human preference: 66.4

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

Model, click to add or removeIndex

Where sources disagree

Across the 35 benchmarks both have, Gemini 3.5 Flash leads 15, GLM 5.3 Flash leads 20. Every overall index that rates both puts Gemini 3.5 Flash ahead.

Overall indexGemini 3.5 Flash (high)GLM 5.3 FlashLeader
BenchLeader Index62.557.8Gemini 3.5 Flash
Arena Text14781475Gemini 3.5 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 3.5 Flash (high)GLM 5.3 Flash
Blended price per 1M tokens$3.38$0.238
Input / output per 1M$1.50 / $9.00$0.150 / $0.500
Cached input per 1M$0.150$0.030
Price per task: chat reply$0.0033$0.0002
Price per task: summarize a 30-page report$0.023$0.0021
Price per task: code edit$0.022$0.0017
Price per task: agentic coding session$0.126$0.011
Price per task: structured extraction$0.0048$0.0004
Agentic coding session, input mostly cached$0.065$0.0056
Cost per benchmark task (AA Index)–$0.583
Output tokens per task (AA Index)–134k
Of which reasoning–103k
Time per task (AA Index)–41 min
Output speed176 tok/s54 tok/s
Time to first answer9.9 s87.0 s
Time to a complete answer, last measured 13 Nov 202627.6 s220.4 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.5 Flash (high) scores 62.5 and takes 10 s to its first answer token; Gemini 3.5 Flash (medium) scores 61.8 in 9 s, Gemini 3.5 Flash (minimal) scores 55.6 in 3 s. GLM 5.3 Flash scores 57.8 and takes 87 s to its first answer token; GLM 5.3 Flash (max) scores 52.4 in 87 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

168 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)GLM 5.3 Flash
BenchLeader IndexBenchLeader62.557.8
Agents & tools scoreBenchLeader62.858.7
Coding scoreBenchLeader59.556.9
Human preference scoreBenchLeader66.866.4
Instruction following scoreBenchLeader74.4–
Knowledge scoreBenchLeader63.345.1
Long context scoreBenchLeader61.264.6
Maths scoreBenchLeader57.768.8
Multimodal scoreBenchLeader66.264.0
Reasoning scoreBenchLeader60.648.3
Blended price $/MBenchLeader$3.38$0.238
Output speedBenchLeader176 tok/s54 tok/s
Time to first answerBenchLeader9.9 s87.0 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub92.8%90.2%†
SimpleBenchSimpleBench76.7%†–
Arena Hard PromptsArena (LMArena)14961500
LiveBench 2.0 ReasoningLiveBench–77.6%†
LiveBench 1.0 ReasoningLiveBench82.0%77.6%
GPQA Diamond (AA)Artificial Analysis92.2%91.2%
Humanity's Last Exam (AA)Artificial Analysis42.7%39.9%
HLE-Diamond (AA)Artificial Analysis–18.2%
GPQA Diamond (Vals)Vals AI92.7%86.4%†
EnigmaEvalScale AI SEAL25.4%–
ARC-AGI-1ARC Prize92.5%91.0%†
ARC-AGI-2ARC Prize72.1%65.8%†
CritPtArtificial Analysis13.1%15.4%
CritPt v2 hard subset (AA)Artificial Analysis–24.5%
Arena ExpertArena (LMArena)14911511
Chess PuzzlesEpoch AI Benchmarking Hub45.0%21.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub32.0%8.0%†
LMCAEpoch AI Benchmarking Hub47.1%–
DTBenchEpoch AI Benchmarking Hub94.7%–
ForecastBenchForecastBench64.0%†–
BTF-3Epoch AI Benchmarking Hub–14.9%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub79.3%–
SciCodeSciCode53.9%51.6%
WeirdMLWeirdML62.6%–
FrontierCodeCognition–31.8%†
Show all 168 benchmarks
MetricPublisherGemini 3.5 Flash (high)GLM 5.3 Flash
Coding
Arena CodingArena (LMArena)15081526
Arena WebDevArena (LMArena)15001609
LiveBench 2.0 CodingLiveBench–70.9%†
LiveBench 1.0 CodingLiveBench78.2%79.0%
LiveCodeBenchVals AI87.6%80.5%†
IOIVals AI–52.5%†
SWE-bench (Vals)Vals AI78.8%92.0%†
Code MigrationVals AI26.8%20.5%†
Code Migration v1.1Vals AI–51.6%†
ProgramBenchVals AI0.0%0.0%†
Vibe Code Bench 1-100Vals AI–16.0%†
Vibe Code Bench v1.1Vals AI48.7%30.8%†
SWE Atlas v1.1Scale AI SEAL–55.3%
SWE Atlas v1.1: Codebase QnAScale AI SEAL–66.9%
SWE Atlas v1.1: Test WritingScale AI SEAL–53.3%
SWE Atlas v1.1: RefactoringScale AI SEAL–45.7%
Surface Evolver BenchEpoch AI Benchmarking Hub58.1%†52.5%†
DeepSWE v1.1Epoch AI Benchmarking Hub36.1%63.4%†
CursorBenchCursor–36.8%†
ALE-BenchEpoch AI Benchmarking Hub911.0303.6†
FrontierSWEEpoch AI Benchmarking Hub–18.1%†
Terminal-Bench 4.0 (AA)Artificial Analysis6.6%32.8%
Terminal-Bench 2.1 (AA)Artificial Analysis78.7%84.3%
GameBench 2 OverallDuelLab GameBench 249.4†54.9
GameBench 2 by reasoning settingDuelLab GameBench 263.257.2†
Design Arena WebsiteDesign Arena1260†1257
FrontierCode 1.1 (AA)Artificial Analysis–41.0%
FrontierCode 2.0 (AA)Artificial Analysis–17.6%
Agents & tools
Terminal-BenchTerminal-Bench–37.0%†
APEX-AgentsMercor27.5%†52.8%
Arena AgentArena (LMArena)–-2.9
LiveBench Long AgenticLiveBench–20.7%†
LiveBench BrowserLiveBench–59.8%†
LiveBench Agentic CodingLiveBench49.0%56.8%
Terminal-Bench HardArtificial Analysis40.9%–
τ²-Bench Telecom (AA)Artificial Analysis95.3%–
Terminal-Bench 2.1 (Vals)Vals AI74.2%62.9%†
MCP AtlasScale AI SEAL83.6%–
HiL-BenchScale AI SEAL27.7%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis–57.1%
GDPval-AA v2.1Artificial Analysis12111648
τ³-Banking (AA)Artificial Analysis32.2%47.2%
ITBench SRE (AA)Artificial Analysis40.4%51.2%
Analyst Agent (AA)Artificial Analysis45.0%25.0%
APEX-Agents (AA)Artificial Analysis47.0%–
CyberBenchVals AI–67.9%†
Finance Agent v2Vals AI57.9%57.9%†
Finance Agent v2.1Vals AI–60.6%†
Harvey's Legal Agent Benchmark v1.1Vals AI–10.4%†
Harvey's Legal Agent Benchmark v1Vals AI2.5%6.7%†
Legal Research BenchVals AI30.8%45.2%†
SkillsBenchVals AI52.7%40.2%†
SREBenchVals AI–0.8%†
Tax Agent BenchVals AI21.6%31.6%†
Terminal-Bench 2.0 (Vals)Vals AI67.4%–
Terminal-Bench 4.0 (Vals)Vals AI6.1%37.4%†
Terminal-Bench ScienceVals AI5.7%2.9%†
Web Search IndexVals AI37.0%–
Arena Agent Task CompletionArena (LMArena)–1.3
PostTrainBenchEpoch AI Benchmarking Hub–36.8%†
GBAEvalEpoch AI Benchmarking Hub6.7%†–
Vending-Bench 2Andon Labs5396.4†–
AutomationBenchArtificial Analysis42.1%60.4%
GDP.pdf (AA)Artificial Analysis19.8%15.4%
Harvey LAB-AA v1.1Harvey–0.8%
EnterpriseOps-GymArtificial Analysis50.1%33.2%
AA-Briefcase v1.1Artificial Analysis8761450
Design Arena AgenticDesign Arena1174†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–4.8%
CWE-Bench (AA)Artificial Analysis–55.8%
DeepSec-Bench (AA)Artificial Analysis–19.9%
CyberGym end-to-end (AA)Artificial Analysis–74.0%
MKA (AA)Artificial Analysis–36.2%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub62.8%55.8%†
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%17.1%†
OTIS Mock AIMEEpoch AI Benchmarking Hub95.6%93.9%†
ProofBenchVals AI31.0%21.0%†
LiveBench MathematicsLiveBench88.2%81.2%
AIME 2026MathArena95.0%–
HMMT February 2026MathArena95.5%–
MathArena ApexMathArena32.3%–
Arena MathsArena (LMArena)14971505
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub66.2%–
LiveBench 2.0 Data AnalysisLiveBench–76.4%†
LiveBench ResearchLiveBench–73.9%†
LiveBench 1.0 Data AnalysisLiveBench64.9%76.4%
AA-Omniscience v1.1Artificial Analysis–0.7
MMLU-ProVals AI89.5%86.1%†
LegalBenchVals AI83.6%83.9%†
CorpFinVals AI64.7%–
TaxEvalVals AI74.4%75.6%†
Excel Modeling BenchmarkVals AI63.5%55.9%†
Excel Modeling Benchmark v1.1Vals AI–66.3%†
MedCodeVals AI55.8%–
MedScribeVals AI76.6%88.9%†
Public Benefits Bench v1.1Vals AI59.5%–
Access to Justice BenchmarkVals AI–71.1%†
Financial Coaching BenchVals AI63.0%–
DrugDiscoveryBenchScale AI SEAL50.0%–
EBR-benchEpoch AI Benchmarking Hub4.8%–
GDP.pdfEpoch AI Benchmarking Hub14.0%†14.0%†
AA-Omniscience v1.1: accuracyArtificial Analysis–28.2%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–61.6%
Instruction following
LiveBench LanguageLiveBench84.6%77.3%
LiveBench Instruction FollowingLiveBench75.6%52.8%
IFBenchArtificial Analysis76.3%–
Arena Instruction FollowingArena (LMArena)14651474
Human preference
Arena TextArena (LMArena)14781475
EQ-Bench 4EQ-Bench1077†–
Arena Creative WritingArena (LMArena)14651435
Arena Multi-turnArena (LMArena)14801476
Arena Longer QueriesArena (LMArena)14831480
Multimodal
Arena VisionArena (LMArena)13081295
LiveBench DesignLiveBench–73.7%†
MMMU-ProArtificial Analysis84.3%–
MMMU-Pro (Vals)Vals AI88.3%86.0%†
MortgageTaxVals AI68.1%–
SAGEVals AI–89.3%†
Humanity's Sixth SenseScale AI SEAL32.6%26.8%†
GeoBenchGeoBench85.0%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub33.6%†–
VIALS-AAHandshake AI–39.8%
Code2Video-AAArtificial Analysis–975
AA-3DArtificial Analysis–937
Long context
AA-LCR v1.1Artificial Analysis73.3%80.0%
Arena DocumentArena (LMArena)1455–
MLCRArtificial Analysis10.0%11.7%
FACTS GroundingGoogle–56.1%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub155.3†153.8
LiveBench 2.0LiveBench–60.7%†
LiveBench 1.0LiveBench74.6%71.6%
AA Intelligence Index v5.0.1Artificial Analysis–27.8
AA Intelligence Index v4.3.2Artificial Analysis32.641.8
AA Progress Index v1Artificial Analysis305.1318.6
Vals IndexVals AI–50.9†
Vals Finance IndexVals AI–55.8%†
Vals Multimodal IndexVals AI62.9%–
Vals Router IndexVals AI–50.9%
Vals Legal IndexVals AI–71.0%†
AA Cyber IndexArtificial Analysis–49.9
Safety & honesty
FORTRESSScale AI SEAL–26.7%
DistressBenchScale AI SEAL66.9%†72.7%
Metadata
AA Openness IndexArtificial Analysis–44.4

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

  • GLM 5.3 Flash: BenchLeader Index 56.7 → 57.8.
  • Gemini 3.5 Flash (high): 1 new result (GDPval-AA v2.1); 1 score revision.
  • Gemini 3.5 Flash (high): 3 new results (AIME 2026, HMMT February 2026, MathArena Apex).
  • GLM 5.3 Flash: 1 score revision.
  • GLM 5.3 Flash: 5 score revisions.
  • GLM 5.3 Flash: 1 new result (FORTRESS).
  • Gemini 3.5 Flash (high): 1 score revision.
  • GLM 5.3 Flash: 2 score revisions; GLM 5.3 Flash cached input price moved from $0.034/M to $0.030/M (13% down).
  • GLM 5.3 Flash: GLM 5.3 Flash cached input price moved from $0.030/M to $0.034/M (15% up).
  • GLM 5.3 Flash: GLM 5.3 Flash cached input price moved from $0.034/M to $0.030/M (13% down).

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

Gemini 3.5 Flash vs GLM 5.3 Flash: questions

Is Gemini 3.5 Flash better than GLM 5.3 Flash?
Gemini 3.5 Flash (high) leads on quality: 62.5 vs 57.8. The BenchLeader Index combines every independent quality benchmark; Gemini 3.5 Flash (high) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Gemini 3.5 Flash vs GLM 5.3 Flash: which is cheaper, and will that change?
GLM 5.3 Flash is cheaper today: $0.238 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 GLM 5.3 Flash better for coding?
Gemini 3.5 Flash scores higher in coding (60 vs 57 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 1609 for GLM 5.3 Flash.
Which is faster, Gemini 3.5 Flash or GLM 5.3 Flash?
Gemini 3.5 Flash streams 3×+ faster (176 vs 54 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.5 Flash or GLM 5.3 Flash better for agents and tool use?
Gemini 3.5 Flash scores higher in agentic tasks (63 vs 59 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 32.2% for Gemini 3.5 Flash against 47.2% for GLM 5.3 Flash.
More questions (4)
Which is better for long documents?
GLM 5.3 Flash scores higher on long-context benchmarks (65 vs 61). Both take about 1M tokens: Gemini 3.5 Flash 1,048,576, GLM 5.3 Flash 1,000,000.
Which has lower latency?
Gemini 3.5 Flash answers first: 9.9 s against 87.0 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 GLM 5.3 Flash?
Across the 35 benchmarks both have, Gemini 3.5 Flash leads 15, GLM 5.3 Flash leads 20. Every overall index that rates both puts Gemini 3.5 Flash ahead.
When was GLM 5.3 Flash released?
GLM 5.3 Flash was released on 20 Aug 2026.