BenchLeader

Claude Opus 4.5 vs GLM 5.3

Full profiles: Claude Opus 4.5 (Anthropic) and GLM 5.3 (Zhipu AI): every benchmark, price and rank.

Updated · Data from 13 sources

As of 16 Nov 2026, Claude Opus 4.5 and GLM 5.3 are neck and neck on quality (59.7 vs 58.8 on the BenchLeader Index, inside the ±4.4 margin), and GLM 5.3 is 4.7× cheaper at $2.15 vs $10.00 per 1M tokens blended. Choose Claude Opus 4.5 for reasoning (67 vs 55), knowledge (60 vs 54), and maths (65 vs 60) and fast first answers (1.1 s vs 57.6 s); choose GLM 5.3 for agents & tools (58 vs 53) and human preference (67 vs 66), where it also streams ~1.5× faster.

Key facts (as of 16 Nov 2026)

  • Claude Opus 4.5 scores 59.7 on the BenchLeader Index and GLM 5.3 scores 58.8 (BenchLeader, 16 Nov 2026).
  • Claude Opus 4.5 costs $10.00 per 1M tokens blended (list price, 16 Nov 2026).
  • GLM 5.3 costs $2.15 per 1M tokens blended (list price, 16 Nov 2026).
  • GLM 5.3 streams ~1.5× faster than Claude Opus 4.5 (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 19 benchmarks both models have, GLM 5.3 leads 10 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Claude Opus 4.5 is rated 1493 and GLM 5.3 1623 (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
CodingEither61 vs 60 category score; Arena WebDev 1493 vs 1623Either
Agents & tool useGLM 5.358 vs 53 category scoreMedium
MathsClaude Opus 4.565 vs 60 category score; Arena Maths 1472 vs 1501Medium
ReasoningClaude Opus 4.567 vs 55 category score; Arena Hard Prompts 1501 vs 1507High
KnowledgeClaude Opus 4.560 vs 54 category score; MMLU-Pro 87.3% vs 86.8%Medium
Chat quality (human preference)GLM 5.367 vs 66 on Arena votesMedium
Lowest costGLM 5.3$2.15 vs $10.00 per 1M blended; agentic coding session $0.102 vs $0.400–
Fastest first answerClaude Opus 4.51.1 s (Claude Opus 4.5 (high)) vs 57.6 s (GLM 5.3 (max)) 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

  • Claude Opus 4.5 (high) and GLM 5.3 (max) are neck and neck on quality (59.7 vs 58.8, within the ±4.4 margin).
  • Claude Opus 4.5 (high) is stronger in coding, knowledge, maths, reasoning.
  • GLM 5.3 (max) is stronger in agents & tools, human preference.
  • GLM 5.3 (max) is 4.7× cheaper ($2.15 vs $10.00 per 1M blended).
  • GLM 5.3 (max) streams 2.2× faster (88 vs 40 tokens per second).

At a glance

SpecClaude Opus 4.5GLM 5.3
DeveloperAnthropicZhipu AI
Released24 Nov 202518 Aug 2026
Context window (tokens)200,0001,000,000
Compared atClaude Opus 4.5 (high)GLM 5.3 (max)
Open weightsNoYes
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$1.40 / $4.40 / $0.260

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.

CategoryClaude Opus 4.5 (high)GLM 5.3 (max)Leader
Reasoning66.654.7Claude Opus 4.5
Coding60.659.7level
Agents & tools52.757.6GLM 5.3
Maths65.360.0Claude Opus 4.5
Knowledge60.053.5Claude Opus 4.5
Human preference66.267.2GLM 5.3
Long context–64.5not 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 & toolsMathsKnowledgeHumanpreferenceClaude Opus 4.5, Reasoning: 66.6Claude Opus 4.5, Coding: 60.6Claude Opus 4.5, Agents & tools: 52.7Claude Opus 4.5, Maths: 65.3Claude Opus 4.5, Knowledge: 60.0Claude Opus 4.5, Human preference: 66.2GLM 5.3, Reasoning: 54.7GLM 5.3, Coding: 59.7GLM 5.3, Agents & tools: 57.6GLM 5.3, Maths: 60.0GLM 5.3, Knowledge: 53.5GLM 5.3, Human preference: 67.2

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 19 benchmarks both have, Claude Opus 4.5 leads 9, GLM 5.3 leads 10. Every overall index that rates both puts GLM 5.3 ahead.

Overall indexClaude Opus 4.5 (high)GLM 5.3 (max)Leader
BenchLeader Index59.758.8neck and neck
Arena Text14741482GLM 5.3

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.

MeasureClaude Opus 4.5 (high)GLM 5.3 (max)
Blended price per 1M tokens$10.00$2.15
Input / output per 1M$5.00 / $25.00$1.40 / $4.40
Cached input per 1M$0.500$0.260
Price per task: chat reply$0.0095$0.0019
Price per task: summarize a 30-page report$0.075$0.019
Price per task: code edit$0.068$0.015
Price per task: agentic coding session$0.400$0.102
Price per task: structured extraction$0.015$0.0037
Agentic coding session, input mostly cached$0.198$0.050
Cost per benchmark task (AA Index)–$5.01
Output tokens per task (AA Index)–119k
Of which reasoning–85k
Time per task (AA Index)–23 min
Output speed40 tok/s88 tok/s
Time to first answer1.1 s57.6 s
Time to a complete answer, last measured 13 Nov 2026–144.1 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.5 (high) scores 59.7 and takes 1 s to its first answer token; Claude Opus 4.5 (thinking) scores 59.3 in 14 s, Claude Opus 4.5 scores 57.1 in 1 s. GLM 5.3 (max) scores 58.8 and takes 58 s to its first answer token; GLM 5.3 (low) scores 47.3 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

195 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.

MetricPublisherClaude Opus 4.5 (high)GLM 5.3 (max)
BenchLeader IndexBenchLeader59.758.8
Agents & tools scoreBenchLeader52.757.6
Coding scoreBenchLeader60.659.7
Human preference scoreBenchLeader66.267.2
Knowledge scoreBenchLeader60.053.5
Maths scoreBenchLeader65.360.0
Reasoning scoreBenchLeader66.654.7
Long context scoreBenchLeader–64.5
Blended price $/MBenchLeader$10.00$2.15
Output speedBenchLeader40 tok/s88 tok/s
Time to first answerBenchLeader1.1 s57.6 s
Context windowBenchLeader200,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub86.0%†90.9%
Humanity's Last ExamScale AI / CAIS25.2%†–
SimpleBenchSimpleBench62.0%†66.2%†
Arena Hard PromptsArena (LMArena)15011507
LiveBench 1.0 ReasoningLiveBench80.1%85.8%†
GPQA Diamond (AA)Artificial Analysis86.6%†91.7%
Humanity's Last Exam (AA)Artificial Analysis30.1%†42.3%
HLE-Diamond (AA)Artificial Analysis–17.9%
GPQA Diamond (Vals)Vals AI85.9%88.1%
Kagi LLM BenchmarkKagi LLM Benchmark70.7%†–
ARC-AGI-1ARC Prize80.0%†–
ARC-AGI-2ARC Prize37.6%†–
CritPtArtificial Analysis4.6%†19.1%
CritPt v2 hard subset (AA)Artificial Analysis–33.5%
MysteryMechanismVals AI–23.0%
SciPredictScale AI SEAL23.1%†–
HLE-Diamond (Scale)Scale AI SEAL–16.4%†
Arena ExpertArena (LMArena)15031522
Chess PuzzlesEpoch AI Benchmarking Hub14.0%†37.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub22.0%†33.0%
CL-benchEpoch AI Benchmarking Hub21.1%†–
LMCAEpoch AI Benchmarking Hub44.5%55.5%†
DTBenchEpoch AI Benchmarking Hub89.9%87.7%†
ForecastBenchForecastBench64.6%†–
BTF-3Epoch AI Benchmarking Hub–14.9%†
Show all 195 benchmarks
MetricPublisherClaude Opus 4.5 (high)GLM 5.3 (max)
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.7%†–
SciCodeSciCode–59.0%
WeirdMLWeirdML63.7%†75.4%
FrontierCodeCognition–40.1%
GSO-BenchGSO-Bench26.5%†–
Arena CodingArena (LMArena)15301522
Arena WebDevArena (LMArena)14931623
LiveBench 1.0 CodingLiveBench79.7%79.0%†
LiveCodeBenchVals AI83.7%80.5%
IOIVals AI–68.4%
SWE-bench (Vals)Vals AI76.4%95.4%
SWE-Bench ProScale AI SEAL45.9%†–
SWE-bench Verified (bash only)SWE-bench76.8%–
SWE-bench Multilingual (bash only)SWE-bench70.7%†–
SWE-bench Verified (any scaffold)SWE-bench79.2%†–
Code MigrationVals AI–44.2%
Code Migration v1.1Vals AI–55.1%
ProgramBenchVals AI–1.5%
Vibe Code Bench 1-100Vals AI–20.0%
Vibe Code Bench v1.1Vals AI20.6%78.1%
Vibe Code Bench 1-100 v1.1Vals AI–29.8%
SWE-Bench Pro (private)Scale AI SEAL23.4%†–
SWE Atlas v1.1Scale AI SEAL–58.1%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL–70.2%†
SWE Atlas v1.1: Test WritingScale AI SEAL–55.6%†
SWE Atlas v1.1: RefactoringScale AI SEAL–48.6%†
SWE-Bench Pro V2Scale AI SEAL–95.6%
SWE-Bench Pro V2 HARDScale AI SEAL–84.3%
DeepSWE v1.1Epoch AI Benchmarking Hub–69.0%
CursorBenchCursor–42.6%
ALE-BenchEpoch AI Benchmarking Hub1025.4†1317.4†
AlgoTuneAlgoTune1.8†–
FrontierSWEEpoch AI Benchmarking Hub–30.2%
WeirdML v3WeirdML6.5%–
Terminal-Bench 4.0 (AA)Artificial Analysis–41.9%
Terminal-Bench 2.1 (AA)Artificial Analysis–83.9%
Startrise FrontendStartrise–73.2%†
GameBench 2 OverallDuelLab GameBench 247.1†64.6†
GameBench 2 by reasoning settingDuelLab GameBench 2–72.3
Design Arena WebsiteDesign Arena1239†1279†
FrontierCode 1.1 (AA)Artificial Analysis–40.1%
FrontierCode 2.0 (AA)Artificial Analysis–21.6%
LiveCodeBench (AA)Artificial Analysis87.1%†–
Agents & tools
Terminal-BenchTerminal-Bench63.1%†41.2%
GDPvalOpenAI45.5%†–
CybenchCybench82.0%†–
Remote Labor IndexScale AI / CAIS3.8%†–
APEX-AgentsMercor–56.6%†
Arena AgentArena (LMArena)–1
LiveBench Agentic CodingLiveBench39.7%60.9%†
Terminal-Bench HardArtificial Analysis47.0%†–
τ²-Bench Telecom (AA)Artificial Analysis89.5%†–
Terminal-Bench 2.1 (Vals)Vals AI–71.5%
MCP AtlasScale AI SEAL69.8%84.2%†
HiL-BenchScale AI SEAL–58.3%†
BFCL OverallBerkeley Function Calling Leaderboard77.5%†–
τ²-benchτ²-bench85.3%–
τ³-bench Bankingτ²-bench24.7%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–57.5%
GDPval-AA v2.1Artificial Analysis–1655
τ³-Banking (AA)Artificial Analysis–50.3%
ITBench SRE (AA)Artificial Analysis–46.1%
Analyst Agent (AA)Artificial Analysis–38.8%
CyberBenchVals AI–72.1%
Finance Agent v2Vals AI–55.8%
Finance Agent v2.1Vals AI–65.0%
Harvey's Legal Agent Benchmark v1.1Vals AI–14.6%
Harvey's Legal Agent Benchmark v1Vals AI–8.3%
Legal Research BenchVals AI–49.0%
Poker AgentVals AI1033.4%†–
SkillsBenchVals AI–47.5%
SREBenchVals AI–9.2%
Tax Agent BenchVals AI–43.3%
Terminal-Bench 2.0 (Vals)Vals AI58.4%–
Terminal-Bench 4.0 (Vals)Vals AI–38.9%
Terminal-Bench ScienceVals AI–5.7%
Arena SearchArena (LMArena)1186†–
Arena Agent Task CompletionArena (LMArena)–3.1
BALROGBALROG43.0%†–
DeepResearch BenchDeepResearch Bench54.8%–
PostTrainBenchEpoch AI Benchmarking Hub–34.5%
METR Time HorizonsMETR75.0%†–
Vending-Bench 2Andon Labs4967.1†8163.6†
AutomationBenchArtificial Analysis–62.2%
GDP.pdf (AA)Artificial Analysis–11.2%
Harvey LAB-AA v1.1Harvey–0.3%
EnterpriseOps-GymArtificial Analysis–36.4%
AA-Briefcase v1.1Artificial Analysis–1501
GDPxGDPx by SemiAnalysis–2.7%
Design Arena AgenticDesign Arena1156†1239†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–9.5%
CWE-Bench (AA)Artificial Analysis–55.8%
DeepSec-Bench (AA)Artificial Analysis–24.3%
CyberGym end-to-end (AA)Artificial Analysis–29.0%
DeepSearchQAGoogle24.0%†–
FACTS SearchGoogle–87.7%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub34.4%†68.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub4.9%†29.3%
OTIS Mock AIMEEpoch AI Benchmarking Hub86.1%†91.1%
ProofBenchVals AI36.0%†49.0%
LiveBench MathematicsLiveBench90.4%87.9%†
AIME (Vals)Vals AI76.9%†–
MGSMVals AI94.8%†–
Arena MathsArena (LMArena)14721501
AIME 2025 (AA)Artificial Analysis91.3%†–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub45.7%†41.0%
LiveBench 1.0 Data AnalysisLiveBench74.4%70.2%†
AA-Omniscience v1.1Artificial Analysis–6.0
MMLU-ProVals AI87.3%86.8%
LegalBenchVals AI84.6%84.8%
CorpFinVals AI65.1%–
TaxEvalVals AI74.9%72.4%
MedQAVals AI93.2%†–
PRBench FinanceScale AI SEAL46.2%†–
PRBench LegalScale AI SEAL44.2%†–
MultiNRCScale AI SEAL41.2%†–
CaseLaw v2Vals AI62.6%†–
Excel Modeling BenchmarkVals AI–56.3%
Excel Modeling Benchmark v1.1Vals AI–69.1%
MedCodeVals AI49.2%42.9%
MedScribeVals AI85.3%88.8%
Public Benefits Bench v1.1Vals AI–68.5%
Access to Justice BenchmarkVals AI–73.7%
Financial Coaching BenchVals AI–74.1%
Immigration BenchVals AI–66.7%
EBR-benchEpoch AI Benchmarking Hub14.3%†–
AA-Omniscience v1.1: accuracyArtificial Analysis–32.3%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–61.1%
Global-MMLU-Lite (AA)Artificial Analysis91.3%†–
HealthBench Professional (AA)OpenAI–52.8%
FACTS ParametricGoogle–40.3%†
Instruction following
LiveBench LanguageLiveBench81.3%79.9%†
LiveBench Instruction FollowingLiveBench62.5%69.3%†
IFBenchArtificial Analysis58.0%†–
MultiChallengeScale AI SEAL59.0%†–
TutorBenchScale AI SEAL49.8%†–
Arena Instruction FollowingArena (LMArena)14831481
Human preference
Arena TextArena (LMArena)14741482
EQ-Bench Creative Writing v3EQ-Bench1686†2076†
Arena Creative WritingArena (LMArena)14691456
Arena Multi-turnArena (LMArena)14851482
Arena Longer QueriesArena (LMArena)14951488
Multimodal
MMMU-ProArtificial Analysis74.0%†–
VISTAScale AI SEAL45.3%†–
MMMU-Pro (Vals)Vals AI83.0%–
MortgageTaxVals AI68.7%–
GeoBenchGeoBench75.0%†–
VPCTEpoch AI Benchmarking Hub40.0%†–
Furniture AssemblyEpoch AI Benchmarking Hub28.3%†–
Code2Video-AAArtificial Analysis–1034
AA-3DArtificial Analysis–794
Long context
AA-LCR v1.1Artificial Analysis77.3%†79.7%
Arena DocumentArena (LMArena)1468†–
MLCRArtificial Analysis–17.2%
FACTS GroundingGoogle–55.2%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub151.9†157.1†
LiveBench 1.0LiveBench72.6%76.1%†
AA Intelligence Index v5.0.1Artificial Analysis–31.6
AA Intelligence Index v4.3.2Artificial Analysis29.1†44.8
AA Progress Index v1Artificial Analysis284.4†322.7
Vals IndexVals AI–59.9
Vals Finance IndexVals AI–61.4%
Vals RSI IndexVals AI14.8%22.9%
Vals Router IndexVals AI–59.7%†
Vals Legal IndexVals AI–74.6%
AA Cyber IndexArtificial Analysis–36.4
Safety & honesty
FORTRESSScale AI SEAL13.6%†28.2%
MASKScale AI SEAL87.1%†–
DistressBenchScale AI SEAL–72.5%†
Metadata
AA Openness IndexArtificial Analysis11.1†33.3

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

  • Claude Opus 4.5 (high): 13 new results (LiveCodeBench, MMLU-Pro, LegalBench…).
  • GLM 5.3 (max): 1 new result (PostTrainBench).
  • GLM 5.3 (max): 4 score revisions.
  • GLM 5.3 (max): 1 score revision; cached input price moved from $0.30/M to $0.26/M (13% down).
  • GLM 5.3 (max): cached input price moved from $0.26/M to $0.30/M (15% up).
  • GLM 5.3 (max): cached input price moved from $0.30/M to $0.26/M (13% down).
  • GLM 5.3 (max): cached input price moved from $0.26/M to $0.30/M (15% up).
  • GLM 5.3 (max): BenchLeader Index 61.3 → 58.9.
  • GLM 5.3 (max): 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $2.01/M to $5.01/M (150% up); cached input price moved from $0.30/M to $0.26/M (13% down).
  • GLM 5.3 (max): cached input price moved from $0.26/M to $0.30/M (15% up).

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

Claude Opus 4.5 vs GLM 5.3: questions

Is Claude Opus 4.5 better than GLM 5.3?
Claude Opus 4.5 (high) and GLM 5.3 (max) are neck and neck on quality (59.7 vs 58.8, within the ±4.4 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.
Claude Opus 4.5 vs GLM 5.3: which is cheaper, and will that change?
GLM 5.3 is cheaper today: $2.15 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 4.5 or GLM 5.3 better for coding?
They are level in coding (61 vs 60 on the category index). On Arena WebDev, the top shared coding benchmark, it is 1493 for Claude Opus 4.5 against 1623 for GLM 5.3.
Which is faster, Claude Opus 4.5 or GLM 5.3?
GLM 5.3 streams ~1.5× faster (88 vs 40 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 4.5 or GLM 5.3 better for agents and tool use?
GLM 5.3 scores higher in agentic tasks (58 vs 53 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
GLM 5.3 accepts more context: 1,000,000 against 200,000 tokens for Claude Opus 4.5.
Which has lower latency?
Claude Opus 4.5 answers first: 1.1 s against 57.6 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 Claude Opus 4.5 vs GLM 5.3?
Across the 19 benchmarks both have, Claude Opus 4.5 leads 9, GLM 5.3 leads 10. Every overall index that rates both puts GLM 5.3 ahead.
When was GLM 5.3 released?
GLM 5.3 was released on 18 Aug 2026.