BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases9

Claude Opus 4.7 vs GLM-5

Full profiles: Claude Opus 4.7 (Anthropic) and GLM-5 (Zhipu AI): every benchmark, price and rank.

Updated · Data from 10 sources

As of 29 Oct 2026, Claude Opus 4.7 is ahead of GLM-5 on quality (63.1 vs 60.2 on the BenchLeader Index), but GLM-5 is 6.5× cheaper at $1.55 vs $10.00 per 1M tokens blended. Choose Claude Opus 4.7 for agents & tools (66 vs 58), knowledge (62 vs 57), and maths (67 vs 63) and fast first answers (1.2 s vs 46.8 s); choose GLM-5 for reasoning (68 vs 65).

Key facts (as of 29 Oct 2026)

  • Claude Opus 4.7 scores 63.1 on the BenchLeader Index and GLM-5 scores 60.2 (BenchLeader, 29 Oct 2026).
  • Claude Opus 4.7 costs $10.00 per 1M tokens blended (list price, 29 Oct 2026).
  • GLM-5 costs $1.55 per 1M tokens blended (list price, 29 Oct 2026).
  • Of the 12 benchmarks both models have, Claude Opus 4.7 leads 11 (BenchLeader, 29 Oct 2026).
Claude Opus 4.7 benchmarks Anthropic GLM-5 benchmarks thinking Zhipu AIOpen 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
CodingClaude Opus 4.761 vs 59 category score; LiveCodeBench 85.1% vs 81.9%Medium
Agents & tool useClaude Opus 4.766 vs 58 category score; Terminal-Bench 2.0 (Vals) 68.5% vs 49.4%High
MathsClaude Opus 4.767 vs 63 category score; AIME (Vals) 96.3% vs 91.7%Medium
ReasoningGLM-568 vs 65 category score; Kagi LLM Benchmark 75.0% vs 73.3%Medium
KnowledgeClaude Opus 4.762 vs 57 category score; MMLU-Pro 89.9% vs 86.0%Medium
Chat quality (human preference)–Only Claude Opus 4.7 has an Arena rating (67 category score)Not comparable
Lowest costGLM-5$1.55 vs $10.00 per 1M blended; agentic coding session $0.073 vs $0.400–
Fastest first answerClaude Opus 4.71.2 s (Claude Opus 4.7) vs 46.8 s (GLM-5 (thinking)) 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 4.7 leads on quality: 63.1 vs 60.2.
  • Claude Opus 4.7 is stronger in agents & tools, coding, human preference, knowledge, maths, multimodal.
  • GLM-5 (thinking) is stronger in reasoning, instruction following, long context.
  • GLM-5 (thinking) is 6.5× cheaper ($1.55 vs $10.00 per 1M blended).

At a glance

SpecClaude Opus 4.7GLM-5
DeveloperAnthropicZhipu AI
Released16 Apr 202611 Feb 2026
Context window (tokens)1,000,000204,800
Compared atClaude Opus 4.7GLM-5 (thinking)
Open weightsNoYes
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$1.00 / $3.20 / $0.149

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 4.7GLM-5 (thinking)Leader
Reasoning64.868.2GLM-5
Coding61.359.1Claude Opus 4.7
Agents & tools65.558.0Claude Opus 4.7
Maths66.663.2Claude Opus 4.7
Knowledge62.257.3Claude Opus 4.7
Instruction following–70.8not comparable
Human preference67.3–not comparable
Multimodal66.8–not comparable
Long context–62.6not comparable

Where sources disagree

Across the 12 benchmarks both have, Claude Opus 4.7 leads 11, GLM-5 leads 1. Every overall index that rates both puts Claude Opus 4.7 ahead.

Overall indexClaude Opus 4.7GLM-5 (thinking)Leader
BenchLeader Index63.160.2Claude Opus 4.7
Arena Text14941457†Claude Opus 4.7

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.

MeasureClaude Opus 4.7GLM-5 (thinking)
Blended price per 1M tokens$10.00$1.55
Input / output per 1M$5.00 / $25.00$1.00 / $3.20
Cached input per 1M$0.500$0.149
Price per task: chat reply$0.0095$0.0014
Price per task: summarize a 30-page report$0.075$0.014
Price per task: code edit$0.068$0.011
Price per task: agentic coding session$0.400$0.073
Price per task: structured extraction$0.015$0.0026
Output speed57 tok/s69 tok/s
Time to first answer1.2 s46.8 s
Time to a complete answer–54.0 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.7 scores 63.1 and takes 1 s to its first answer token; Claude Opus 4.7 (high) scores 60.9 in 1 s, Claude Opus 4.7 (max) scores 59.6 in 21 s. GLM-5 (thinking) scores 60.2 and takes 47 s to its first answer token; GLM-5 scores 54.9 in 2 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

111 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 4.7GLM-5 (thinking)
BenchLeader IndexBenchLeader63.160.2
Agents & tools scoreBenchLeader65.558.0
Coding scoreBenchLeader61.359.1
Human preference scoreBenchLeader67.3–
Knowledge scoreBenchLeader62.257.3
Maths scoreBenchLeader66.663.2
Multimodal scoreBenchLeader66.8–
Reasoning scoreBenchLeader64.868.2
Instruction following scoreBenchLeader–70.8
Long context scoreBenchLeader–62.6
Blended price $/MBenchLeader$10.00$1.55
Output speedBenchLeader57 tok/s69 tok/s
Time to first answerBenchLeader1.2 s46.8 s
Context windowBenchLeader1,000,000 tokens204,800 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub86.4%†87.8%†
Humanity's Last ExamScale AI / CAIS36.2%–
SimpleBenchSimpleBench61.7%53.2%†
Arena Hard PromptsArena (LMArena)15191478†
LiveBench 1.0 ReasoningLiveBench87.2%†–
GPQA Diamond (AA)Artificial Analysis91.4%†82.0%
Humanity's Last Exam (AA)Artificial Analysis42.3%†29.3%
GPQA Diamond (Vals)Vals AI90.2%83.3%
Kagi LLM BenchmarkKagi LLM Benchmark73.3%75.0%
ARC-AGI-1ARC Prize–44.7%†
ARC-AGI-2ARC Prize–4.9%†
ARC-AGI-3ARC Prize0.2%†–
CritPtArtificial Analysis12.0%†2.0%
Chess PuzzlesEpoch AI Benchmarking Hub41.0%†–
Mystery Game PuzzlesEpoch AI Benchmarking Hub13.0%–
CL-benchEpoch AI Benchmarking Hub–18.7%†
LMCAEpoch AI Benchmarking Hub52.2%†–
DTBenchEpoch AI Benchmarking Hub94.7%†–
ForecastBenchForecastBench63.1%63.7%†
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub83.5%†72.1%†
SciCodeSciCode54.5%†–
WeirdMLWeirdML76.4%48.2%†
FrontierCodeCognition38.5%–
GSO-BenchGSO-Bench44.1%–
Arena CodingArena (LMArena)15461498†
Show all 111 benchmarks
MetricPublisherClaude Opus 4.7GLM-5 (thinking)
Coding
Arena WebDevArena (LMArena)15551436†
LiveBench 1.0 CodingLiveBench82.1%†–
LiveCodeBenchVals AI85.1%81.9%
SWE-bench (Vals)Vals AI82.0%71.4%
SWE-bench Verified (bash only)SWE-bench–72.8%†
SWE-bench Verified (any scaffold)SWE-bench–72.8%†
Code MigrationVals AI43.9%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI71.0%23.4%
SWE Atlas: Codebase QnAScale AI SEAL40.3%20.5%†
SWE Atlas: RefactoringScale AI SEAL48.6%24.2%†
SWE Atlas: Test WritingScale AI SEAL38.5%28.7%†
MirrorCodeEpoch AI Benchmarking Hub31.1%†–
ALE-BenchEpoch AI Benchmarking Hub1323.0765.6†
Terminal-Bench 2.1 (AA)Artificial Analysis83.2%†–
Agents & tools
Terminal-BenchTerminal-Bench80.2%52.4%†
OSWorld-Verified 2.0OSWorld18.2%†–
APEX-AgentsMercor49.2%†–
LiveBench Agentic CodingLiveBench50.7%†–
Terminal-Bench HardArtificial Analysis51.5%†43.2%
τ²-Bench Telecom (AA)Artificial Analysis88.6%†98.3%
Terminal-Bench 2.1 (Vals)Vals AI68.5%–
MCP AtlasScale AI SEAL79.1%†–
HiL-BenchScale AI SEAL41.7%–
τ²-benchτ²-bench–81.0%
τ³-bench Bankingτ²-bench40.2%†9.8%
τ³-Banking (AA)Artificial Analysis34.6%†–
ITBench SRE (AA)Artificial Analysis46.7%†–
Analyst Agent (AA)Artificial Analysis43.8%†–
APEX-Agents (AA)Artificial Analysis–14.4%
Finance Agent v2Vals AI51.5%–
Harvey's Legal Agent Benchmark v1Vals AI6.7%–
Legal Research BenchVals AI38.5%–
Tax Agent BenchVals AI23.7%–
Terminal-Bench 2.0 (Vals)Vals AI68.5%49.4%
Arena SearchArena (LMArena)1210–
PostTrainBenchEpoch AI Benchmarking Hub28.6%†–
ExploitBenchEpoch AI Benchmarking Hub26.5%–
GBAEvalEpoch AI Benchmarking Hub43.8%–
Vending-Bench 2Andon Labs10936.84432.1†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub70.2%†–
FrontierMath Tier 4Epoch AI Benchmarking Hub31.7%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub86.7%†80.0%†
ProofBenchVals AI54.0%†–
LiveBench MathematicsLiveBench92.8%†–
AIME (Vals)Vals AI96.3%91.7%
AIME 2026MathArena95.8%†96.7%†
HMMT February 2026MathArena93.9%†86.4%†
USAMO 2026MathArena–35.1%†
MathArena ApexMathArena40.6%†10.9%†
Arena MathsArena (LMArena)14911444†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub51.7%†–
LiveBench 1.0 Data AnalysisLiveBench78.3%†–
MMLU-ProVals AI89.9%86.0%
LegalBenchVals AI85.3%84.1%
CorpFinVals AI66.1%62.9%
TaxEvalVals AI75.3%70.0%
MedQAVals AI–94.3%
CaseLaw v2Vals AI68.4%52.5%
Excel Modeling BenchmarkVals AI63.7%–
MedCodeVals AI54.9%–
MedScribeVals AI83.0%–
EBR-benchEpoch AI Benchmarking Hub19.1%†–
GDP.pdfEpoch AI Benchmarking Hub21.0%†–
Instruction following
LiveBench LanguageLiveBench77.9%†–
LiveBench Instruction FollowingLiveBench66.7%†–
IFBenchArtificial Analysis58.6%†72.3%
Arena Instruction FollowingArena (LMArena)14931447†
Human preference
Arena TextArena (LMArena)14941457†
EQ-Bench 4EQ-Bench1293–
Arena Creative WritingArena (LMArena)14831448†
Arena Multi-turnArena (LMArena)15141471†
Arena Longer QueriesArena (LMArena)15081468†
Multimodal
Arena VisionArena (LMArena)1317–
MMMU-ProArtificial Analysis78.8%†–
MMMU-Pro (Vals)Vals AI85.5%–
MortgageTaxVals AI70.3%–
Blueprint-Bench 2Epoch AI Benchmarking Hub24.5%–
Long context
AA-LCR v1.1Artificial Analysis78.7%†75.7%
Arena DocumentArena (LMArena)1494–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.7145.8†
LiveBench 1.0LiveBench76.5%†–
AA Intelligence Index v4.3.2Artificial Analysis40.7†27.9
AA Progress Index v1Artificial Analysis312.5†280.9
Vals RSI IndexVals AI19.1%†–
Vals Multimodal IndexVals AI67.4%–

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

What changed

  • GLM-5 (thinking): cached input price moved from $0.20/M to $0.15/M (25% down).
  • GLM-5 (thinking): BenchLeader Index 60.6 → 60.1.
  • GLM-5 (thinking): 1 new result (AA Progress Index v1); cached input price moved from $0.15/M to $0.20/M (34% up).
  • GLM-5 (thinking): cached input price moved from $0.20/M to $0.15/M (25% down).
  • GLM-5 (thinking): cached input price moved from $0.15/M to $0.20/M (34% up).
  • Claude Opus 4.7: 1 score revision.
  • GLM-5 (thinking): cached input price moved from $0.20/M to $0.15/M (25% down).
  • GLM-5 (thinking): cached input price moved from $0.15/M to $0.20/M (34% up).
  • Claude Opus 4.7: 1 new result (Harvey's Legal Agent Benchmark v1).
  • Claude Opus 4.7: 1 score revision.

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

Claude Opus 4.7 vs GLM-5: questions

Is Claude Opus 4.7 better than GLM-5?
Claude Opus 4.7 leads on quality: 63.1 vs 60.2. The BenchLeader Index combines every independent quality benchmark; Claude Opus 4.7 is ahead overall as of 29 Oct 2026, but check the category scores for your use.
Claude Opus 4.7 vs GLM-5: which is cheaper, and will that change?
GLM-5 is cheaper today: $1.55 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 4.7 or GLM-5 better for coding?
Claude Opus 4.7 scores higher in coding (61 vs 59 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 85.1% for Claude Opus 4.7 against 81.9% for GLM-5.
Which is faster, Claude Opus 4.7 or GLM-5?
GLM-5 streams faster (69 vs 57 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 4.7 or GLM-5 better for agents and tool use?
Claude Opus 4.7 scores higher in agentic tasks (66 vs 58 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Claude Opus 4.7 accepts more context: 1,000,000 against 204,800 tokens for GLM-5.
Which has lower latency?
Claude Opus 4.7 answers first: 1.2 s against 46.8 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 Claude Opus 4.7 vs GLM-5?
Across the 12 benchmarks both have, Claude Opus 4.7 leads 11, GLM-5 leads 1. Every overall index that rates both puts Claude Opus 4.7 ahead.
When was Claude Opus 4.7 released?
Claude Opus 4.7 was released on 16 Apr 2026.