BenchLeader

Claude Opus 5 vs Grok 4.7

Full profiles: Claude Opus 5 (Anthropic) and Grok 4.7 (SpaceXAI): every benchmark, price and rank.

Updated · Data from 14 sources

As of 16 Nov 2026, Claude Opus 5 is ahead of Grok 4.7 on quality (65.0 vs 57.4 on the BenchLeader Index), but Grok 4.7 is 3.3× cheaper at $3.00 vs $10.00 per 1M tokens blended. Claude Opus 5 leads in every category we measure both in.

Key facts (as of 16 Nov 2026)

  • Claude Opus 5 scores 65.0 on the BenchLeader Index and Grok 4.7 scores 57.4 (BenchLeader, 16 Nov 2026).
  • Claude Opus 5 costs $10.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Grok 4.7 costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 77 benchmarks both models have, Claude Opus 5 leads 67 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Claude Opus 5 is rated 1691 and Grok 4.7 1641 (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
CodingClaude Opus 567 vs 61 category score; Arena WebDev 1691 vs 1641Medium
Agents & tool useClaude Opus 564 vs 57 category score; Terminal-Bench 52.1% vs 38.8%Medium
MathsClaude Opus 570 vs 56 category score; FrontierMath Tiers 1–3 85.6% vs 53.0%High
ReasoningClaude Opus 566 vs 56 category score; GPQA Diamond 93.9% vs 92.7%High
KnowledgeClaude Opus 565 vs 60 category score; SimpleQA Verified 59.9% vs 56.0%Medium
Long documentsClaude Opus 564 vs 63 category score; AA-LCR v1.1 79.3% vs 76.7%Medium
Images and other mediaClaude Opus 567 vs 56 category score; Furniture Assembly 60.8% vs 20.8%High
Chat quality (human preference)Claude Opus 568 vs 63 on Arena votesMedium
Lowest costGrok 4.7$3.00 vs $10.00 per 1M blended; agentic coding session $0.144 vs $0.400–
Fastest first answerEither48.5 s (Claude Opus 5 (max)) vs 55.9 s (Grok 4.7 (xhigh)) 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 5 (max) leads on quality: 65.0 vs 57.4.
  • Claude Opus 5 (max) is stronger in agents & tools, coding, human preference, knowledge, long context, maths, multimodal, reasoning.
  • Grok 4.7 (xhigh) is 3.3× cheaper ($3.00 vs $10.00 per 1M blended).

At a glance

SpecClaude Opus 5Grok 4.7
DeveloperAnthropicSpaceXAI
Released24 Jul 202621 Sep 2026
Context window (tokens)1,000,000500,000
Compared atClaude Opus 5 (max)Grok 4.7 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$2.00 / $6.00 / $0.500

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 5 (max)Grok 4.7 (xhigh)Leader
Reasoning66.155.6Claude Opus 5
Coding67.060.9Claude Opus 5
Agents & tools63.856.9Claude Opus 5
Maths69.855.8Claude Opus 5
Knowledge65.259.9Claude Opus 5
Human preference68.162.5Claude Opus 5
Multimodal67.255.5Claude Opus 5
Long context64.362.9Claude Opus 5
Composite–52.8not 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 & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceClaude Opus 5, Reasoning: 66.1Claude Opus 5, Coding: 67.0Claude Opus 5, Agents & tools: 63.8Claude Opus 5, Maths: 69.8Claude Opus 5, Knowledge: 65.2Claude Opus 5, Long context: 64.3Claude Opus 5, Multimodal: 67.2Claude Opus 5, Human preference: 68.1Grok 4.7, Reasoning: 55.6Grok 4.7, Coding: 60.9Grok 4.7, Agents & tools: 56.9Grok 4.7, Maths: 55.8Grok 4.7, Knowledge: 59.9Grok 4.7, Long context: 62.9Grok 4.7, Multimodal: 55.5Grok 4.7, Human preference: 62.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 77 benchmarks both have, Claude Opus 5 leads 67, Grok 4.7 leads 9 and 1 is a tie. Every overall index that rates both puts Claude Opus 5 ahead.

Overall indexClaude Opus 5 (max)Grok 4.7 (xhigh)Leader
BenchLeader Index65.057.4Claude Opus 5
AA Intelligence Index v5.0.144.235.5Claude Opus 5
Arena Text14891443Claude Opus 5

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 5 (max)Grok 4.7 (xhigh)
Blended price per 1M tokens$10.00$3.00
Input / output per 1M$5.00 / $25.00$2.00 / $6.00
Cached input per 1M$0.500$0.500
Price per task: chat reply$0.0095$0.0026
Price per task: summarize a 30-page report$0.075$0.028
Price per task: code edit$0.068$0.021
Price per task: agentic coding session$0.400$0.144
Price per task: structured extraction$0.015$0.0052
Agentic coding session, input mostly cached$0.198$0.076
Cost per benchmark task (AA Index)$11.82$7.77
Output tokens per task (AA Index)118k105k
Of which reasoning73k69k
Time per task (AA Index)25 min26 min
Output speed80 tok/s68 tok/s
Time to first answer48.5 s55.9 s
Time to a complete answer, last measured 13 Nov 2026191.6 s145.5 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $11.82 on Claude Opus 5 (max) and $7.77 on Grok 4.7 (xhigh), and Claude Opus 5 (max) wrote 1.1× as many output tokens for the same work.

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5 (max) scores 65.0 and takes 49 s to its first answer token; Claude Opus 5 (high) scores 64.4 in 17 s, Claude Opus 5 scores 63.2 in 2 s. Grok 4.7 (xhigh) scores 57.4 and takes 56 s to its first answer token; Grok 4.7 (high) scores 56.9 in 35 s, Grok 4.7 (low) scores 55.4 in 10 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

187 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 5 (max)Grok 4.7 (xhigh)
BenchLeader IndexBenchLeader65.057.4
Agents & tools scoreBenchLeader63.856.9
Coding scoreBenchLeader67.060.9
Human preference scoreBenchLeader68.162.5
Knowledge scoreBenchLeader65.259.9
Long context scoreBenchLeader64.362.9
Maths scoreBenchLeader69.855.8
Multimodal scoreBenchLeader67.255.5
Reasoning scoreBenchLeader66.155.6
Composite scoreBenchLeader–52.8
Blended price $/MBenchLeader$10.00$3.00
Output speedBenchLeader80 tok/s68 tok/s
Time to first answerBenchLeader48.5 s55.9 s
Context windowBenchLeader1,000,000 tokens500,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.9%92.7%
SimpleBenchSimpleBench80.6%†–
Arena Hard PromptsArena (LMArena)15131466
LiveBench 2.0 ReasoningLiveBench–82.7%
LiveBench 1.0 ReasoningLiveBench91.2%82.7%
GPQA Diamond (AA)Artificial Analysis93.2%–
Humanity's Last Exam (AA)Artificial Analysis54.9%43.1%
HLE-Diamond (AA)Artificial Analysis44.8%23.2%
GPQA Diamond (Vals)Vals AI93.4%†–
ARC-AGI-1ARC Prize97.5%89.5%
ARC-AGI-2ARC Prize90.4%61.4%
ARC-AGI-3ARC Prize30.2%†7.0%
CritPtArtificial Analysis29.1%17.7%
CritPt v2 hard subset (AA)Artificial Analysis50.0%33.5%
MysteryMechanismVals AI37.4%25.2%
HLE-Diamond (Scale)Scale AI SEAL38.6%†23.4%†
Arena ExpertArena (LMArena)15301478
Chess PuzzlesEpoch AI Benchmarking Hub43.0%41.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub59.0%29.0%
LMCAEpoch AI Benchmarking Hub63.3%49.4%
DTBenchEpoch AI Benchmarking Hub97.6%96.0%
ForecastBenchForecastBench66.6%–
BTF-3Epoch AI Benchmarking Hub12.0%†–
Coding
SciCodeSciCode56.4%57.4%
WeirdMLWeirdML91.8%–
Show all 187 benchmarks
MetricPublisherClaude Opus 5 (max)Grok 4.7 (xhigh)
Coding
FrontierCodeCognition53.4%47.6%†
Arena CodingArena (LMArena)15281493
Arena WebDevArena (LMArena)16911641
LiveBench 2.0 CodingLiveBench–73.1%
LiveBench 1.0 CodingLiveBench81.5%77.2%
LiveCodeBenchVals AI89.0%–
IOIVals AI84.3%57.7%
SWE-bench (Vals)Vals AI97.0%†–
Code MigrationVals AI57.5%44.8%
Code Migration v1.1Vals AI–53.2%
ProgramBenchVals AI3.0%0.5%
SWE-bench MultimodalVals AI–42.9%
Vibe Code Bench 1-100Vals AI28.5%–
Vibe Code Bench v1.1Vals AI88.4%†86.2%
Vibe Code Bench 1-100 v1.1Vals AI–26.4%
SWE Atlas v1.0: Codebase QnAScale AI SEAL63.2%†–
SWE Atlas v1.0: Test WritingScale AI SEAL62.2%†–
SWE Atlas v1.1Scale AI SEAL–62.1%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL–73.4%†
SWE Atlas v1.1: Test WritingScale AI SEAL–64.4%†
SWE Atlas v1.1: RefactoringScale AI SEAL–48.6%†
SWE-Bench Pro V2Scale AI SEAL99.4%†–
SWE-Bench Pro V2 HARDScale AI SEAL98.0%†–
MirrorCodeEpoch AI Benchmarking Hub87.8%54.4%
DeepSWE v1.1Epoch AI Benchmarking Hub73.7%–
CursorBenchCursor46.6%46.3%
ALE-BenchEpoch AI Benchmarking Hub2164.6†1545.8
FrontierSWEEpoch AI Benchmarking Hub52.0%29.5%
WeirdML v3WeirdML19.0%†8.4%
Terminal-Bench 4.0 (AA)Artificial Analysis49.0%25.8%
Terminal-Bench 2.1 (AA)Artificial Analysis89.1%–
Startrise FrontendStartrise82.3%†75.9%†
GameBench 2 OverallDuelLab GameBench 276.5†63.6†
GameBench 2 by reasoning settingDuelLab GameBench 284.8†71.2
Design Arena WebsiteDesign Arena1304†1244†
FrontierCode 1.1 (AA)Artificial Analysis–33.8%
FrontierCode 2.0 (AA)Artificial Analysis31.1%28.7%
Agents & tools
Terminal-BenchTerminal-Bench52.1%38.8%
OSWorld-Verified 2.0OSWorld31.4%–
APEX-AgentsMercor65.8%54.6%†
Arena AgentArena (LMArena)7.22.6
LiveBench Long AgenticLiveBench–45.3%
LiveBench BrowserLiveBench–49.3%
LiveBench Agentic CodingLiveBench65.2%54.0%
Terminal-Bench 2.1 (Vals)Vals AI84.6%†73.4%
MCP AtlasScale AI SEAL85.8%†–
HiL-BenchScale AI SEAL57.0%†–
τ³-bench Bankingτ²-bench48.7%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–60.7%
GDPval-AA v2.1Artificial Analysis17291717
τ³-Banking (AA)Artificial Analysis42.1%–
ITBench SRE (AA)Artificial Analysis–42.1%
Analyst Agent (AA)Artificial Analysis53.8%52.5%
CUA-benchVals AI9.0%–
CyberBenchVals AI65.4%69.5%
Finance Agent v2Vals AI58.6%52.3%
Finance Agent v2.1Vals AI–60.6%
Harvey's Legal Agent Benchmark v1.1Vals AI–18.3%
Harvey's Legal Agent Benchmark v1Vals AI6.7%12.5%
Legal Research BenchVals AI55.3%47.1%
Robo-benchVals AI–0.2%
SkillsBenchVals AI60.4%–
SREBenchVals AI12.2%3.8%
Tax Agent BenchVals AI47.1%35.8%
Terminal-Bench 4.0 (Vals)Vals AI53.5%28.8%
Terminal-Bench ScienceVals AI27.1%10.0%
Time Horizon Index: KSPVals AI18.8%–
Arena SearchArena (LMArena)1213†–
Arena Agent Task CompletionArena (LMArena)10.25.1
BALROGBALROG63.4%–
PostTrainBenchEpoch AI Benchmarking Hub35.7%†–
GBAEvalEpoch AI Benchmarking Hub79.6%†–
Vending-Bench 2Andon Labs11181.9†10536.8†
AutomationBenchArtificial Analysis56.6%65.6%
GDP.pdf (AA)Artificial Analysis21.6%20.0%
Harvey LAB-AA v1.1Harvey–9.4%
EnterpriseOps-GymArtificial Analysis47.5%–
AA-Briefcase v1.1Artificial Analysis16541636
GDPxGDPx by SemiAnalysis–3.9%
Design Arena AgenticDesign Arena1270†1277†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis28.6%11.4%
CWE-Bench (AA)Artificial Analysis–68.3%
DeepSec-Bench (AA)Artificial Analysis25.9%26.9%
CyberGym end-to-end (AA)Artificial Analysis–74.0%
MKA (AA)Artificial Analysis–40.1%
FACTS SearchGoogle–85.6%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub85.6%53.0%
FrontierMath Tier 4Epoch AI Benchmarking Hub73.2%17.1%
OTIS Mock AIMEEpoch AI Benchmarking Hub98.9%98.1%
ProofBenchVals AI99.0%26.0%†
LiveBench MathematicsLiveBench95.7%95.7%
Arena MathsArena (LMArena)15151447
FrontierMath ErdősEpoch AI Benchmarking Hub0.0%0.0%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub59.9%56.0%
LiveBench 2.0 Data AnalysisLiveBench–76.9%
LiveBench ResearchLiveBench–89.5%
LiveBench 1.0 Data AnalysisLiveBench74.5%76.9%
AA-Omniscience v1.1Artificial Analysis37.631.2
MMLU-ProVals AI91.6%–
LegalBenchVals AI87.0%84.4%
CorpFinVals AI73.2%†–
TaxEvalVals AI75.1%†–
PRBench LegalScale AI SEAL–47.6%
BioMysteryBenchVals AI79.3%69.3%
Excel Modeling BenchmarkVals AI73.6%67.0%
Excel Modeling Benchmark v1.1Vals AI–71.5%
MedCodeVals AI63.6%49.5%
MedScribeVals AI91.0%89.4%
Public Benefits Bench v1.1Vals AI76.9%65.6%
Access to Justice BenchmarkVals AI–73.7%
Financial Coaching BenchVals AI–74.1%
Immigration BenchVals AI–68.0%
DrugDiscoveryBenchScale AI SEAL53.7%–
EBR-benchEpoch AI Benchmarking Hub45.7%–
GDP.pdfEpoch AI Benchmarking Hub24.0%22.8%
AA-Omniscience v1.1: accuracyArtificial Analysis60.9%42.7%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.6%80.0%
HealthBench Professional (AA)OpenAI–55.8%
FACTS ParametricGoogle48.8%†54.3%†
Instruction following
LiveBench LanguageLiveBench88.7%80.1%
LiveBench Instruction FollowingLiveBench63.8%75.3%
Arena Instruction FollowingArena (LMArena)14941435
Human preference
Arena TextArena (LMArena)14891443
EQ-Bench 4EQ-Bench1365†–
EQ-Bench Creative Writing v3EQ-Bench2135†2012†
Arena Creative WritingArena (LMArena)14731421
Arena Multi-turnArena (LMArena)14861435
Arena Longer QueriesArena (LMArena)15021454
Multimodal
Arena VisionArena (LMArena)1318†1230
LiveBench DesignLiveBench–75.0%
MMMU-ProArtificial Analysis84.7%78.2%†
MMMU-Pro (Vals)Vals AI89.9%–
MortgageTaxVals AI72.1%†–
SAGEVals AI–88.7%
Humanity's Sixth SenseScale AI SEAL30.5%–
GeoBenchGeoBench–61.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub30.4%†32.5%†
Furniture AssemblyEpoch AI Benchmarking Hub60.8%20.8%
VIALS-AAHandshake AI–37.9%
Code2Video-AAArtificial Analysis–1127
AA-3DArtificial Analysis–992
FACTS MultimodalGoogle–40.9%†
Long context
AA-LCR v1.1Artificial Analysis79.3%76.7%
Arena DocumentArena (LMArena)1486†–
MLCRArtificial Analysis11.1%20.0%
FACTS GroundingGoogle–68.6%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub164.7†156.2†
LiveBench 2.0LiveBench–67.9%
LiveBench 1.0LiveBench80.1%77.4%
AA Intelligence Index v5.0.1Artificial Analysis44.235.5
AA Intelligence Index v4.3.2Artificial Analysis50.846.5
AA Progress Index v1Artificial Analysis333.7322.7
Vals IndexVals AI–58.6
Vals Finance IndexVals AI–58.8%
Vals RSI IndexVals AI33.0%20.2%
Vals Science IndexVals AI47.9%34.8%
Vals Multimodal IndexVals AI73.9%†–
Vals Router IndexVals AI–58.6%†
Vals Legal IndexVals AI–72.7%
AA Cyber IndexArtificial Analysis–56.4
Safety & honesty
FORTRESSScale AI SEAL16.8%†–
DistressBenchScale AI SEAL70.2%†52.4%†

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

  • Grok 4.7 (xhigh): BenchLeader Index 58.0 → 57.4.
  • Claude Opus 5 (max): 25 new results (LiveCodeBench, MMLU-Pro, IOI…).
  • Grok 4.7 (xhigh): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • Claude Opus 5 (max): 1 new result (GDPval-AA v2.1).
  • Claude Opus 5 (max): 1 new result (MirrorCode).
  • Grok 4.7 (xhigh): 1 new result (MirrorCode).
  • Claude Opus 5 (max): BenchLeader Index 65.5 → 65.0.
  • Grok 4.7 (xhigh): 1 new result (ALE-Bench).
  • Grok 4.7 (xhigh): 2 score revisions.
  • Claude Opus 5 (max): 7 new results (AA Intelligence Index v5.0.1, HLE-Diamond (AA), AA-Omniscience v1.1…).

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

Claude Opus 5 vs Grok 4.7: questions

Is Claude Opus 5 better than Grok 4.7?
Claude Opus 5 (max) leads on quality: 65.0 vs 57.4. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5 (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Claude Opus 5 vs Grok 4.7: which is cheaper, and will that change?
Grok 4.7 is cheaper today: $3.00 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 5 or Grok 4.7 better for coding?
Claude Opus 5 scores higher in coding (67 vs 61 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1691 for Claude Opus 5 against 1641 for Grok 4.7.
Which is faster, Claude Opus 5 or Grok 4.7?
Claude Opus 5 streams faster (80 vs 68 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 5 or Grok 4.7 better for agents and tool use?
Claude Opus 5 scores higher in agentic tasks (64 vs 57 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 52.1% for Claude Opus 5 against 38.8% for Grok 4.7.
More questions (4)
Which is better for long documents?
Claude Opus 5 scores higher on long-context benchmarks (64 vs 63). Claude Opus 5 accepts more context: 1,000,000 against 500,000 tokens for Grok 4.7.
Which has lower latency?
Claude Opus 5 answers first: 48.5 s against 55.9 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 5 vs Grok 4.7?
Across the 77 benchmarks both have, Claude Opus 5 leads 67, Grok 4.7 leads 9 and 1 is a tie. Every overall index that rates both puts Claude Opus 5 ahead.
When was Grok 4.7 released?
Grok 4.7 was released on 21 Sep 2026.