BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases9

Claude Opus 5 vs Gemini 3 Pro

Full profiles: Claude Opus 5 (Anthropic) and Gemini 3 Pro (Google): every benchmark, price and rank.

Updated · Data from 17 sources

As of 26 Oct 2026, Claude Opus 5 (max) is the better pick for most workloads: it leads on quality (68.8 vs 60.4 on the BenchLeader Index). Claude Opus 5 leads in every category we measure both in.

Claude Opus 5 benchmarks max Anthropic Gemini 3 Pro benchmarks 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
CodingClaude Opus 570 vs 58 category score; Arena WebDev 1691 vs 1440High
Agents & tool useClaude Opus 564 vs 62 category score; Terminal-Bench 51.8% vs 69.4%Medium
MathsClaude Opus 571 vs 54 category score; Arena Maths 1517 vs 1477High
ReasoningClaude Opus 574 vs 66 category score; GPQA Diamond 93.9% vs 92.6%High
KnowledgeClaude Opus 572 vs 56 category scoreHigh
Images and other mediaClaude Opus 568 vs 66 category scoreMedium
Chat quality (human preference)Either69 vs 68 on Arena votesEither
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: 68.8 vs 60.4.
  • Claude Opus 5 (max) is stronger in agents & tools, coding, composite, human preference, knowledge, long context, maths, multimodal, reasoning.
  • Gemini 3 Pro is stronger in instruction following.

At a glance

SpecClaude Opus 5Gemini 3 Pro
DeveloperAnthropicGoogle
Released24 Jul 202618 Nov 2025
Context window (tokens)1,000,000–
Compared atClaude Opus 5 (max)Gemini 3 Pro
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $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)Gemini 3 ProLeader
Reasoning74.165.6Claude Opus 5
Coding70.257.9Claude Opus 5
Agents & tools64.361.8Claude Opus 5
Maths70.654.3Claude Opus 5
Knowledge71.656.0Claude Opus 5
Instruction following–60.4not comparable
Human preference68.567.8level
Multimodal67.965.6Claude Opus 5
Long context64.7–not comparable
Composite86.3–not comparable

Where sources disagree

Across the 17 benchmarks both have, Claude Opus 5 leads 14, Gemini 3 Pro leads 3. Every overall index that rates both puts Claude Opus 5 ahead.

Overall indexClaude Opus 5 (max)Gemini 3 ProLeader
BenchLeader Index68.860.4Claude Opus 5
AA Intelligence Index v4.3.250.822.3†Claude Opus 5
Arena Text14911486Claude 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; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

MeasureClaude Opus 5 (max)Gemini 3 Pro
Blended price per 1M tokens$10.00–
Input / output per 1M$5.00 / $25.00– / –
Cached input per 1M$0.500–
Price per task: chat reply$0.0095–
Price per task: summarize a 30-page report$0.075–
Price per task: code edit$0.068–
Price per task: agentic coding session$0.400–
Price per task: structured extraction$0.015–
Cost to run a full benchmark suite$5.86–
Output speed51 tok/s–
Time to first answer68.7 s–
Time to a complete answer78.4 s–

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5 (max) scores 68.8 and takes 69 s to its first answer token; Claude Opus 5 (high) scores 67.9 in 17 s, Claude Opus 5 (xhigh) scores 67.4 in 31 s. Gemini 3 Pro scores 60.4; Gemini 3 Pro (high) scores 60.0, Gemini 3 Pro (low) scores 53.8. 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

173 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)Gemini 3 Pro
BenchLeader IndexBenchLeader68.860.4
Agents & tools scoreBenchLeader64.361.8
Coding scoreBenchLeader70.257.9
Composite scoreBenchLeader86.3–
Human preference scoreBenchLeader68.567.8
Knowledge scoreBenchLeader71.656.0
Long context scoreBenchLeader64.7–
Maths scoreBenchLeader70.654.3
Multimodal scoreBenchLeader67.965.6
Reasoning scoreBenchLeader74.165.6
Instruction following scoreBenchLeader–60.4
Blended price $/MBenchLeader$10.00–
Output speedBenchLeader51 tok/s–
Time to first answerBenchLeader68.7 s–
Context windowBenchLeader1,000,000 tokens–
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.9%92.6%
Humanity's Last ExamScale AI / CAIS–37.5%
SimpleBenchSimpleBench80.6%†76.4%
Arena Hard PromptsArena (LMArena)15151502
LiveBench 1.0 ReasoningLiveBench91.2%–
GPQA Diamond (AA)Artificial Analysis93.2%90.8%†
Humanity's Last Exam (AA)Artificial Analysis54.9%39.7%†
GPQA Diamond (Vals)Vals AI93.4%†91.7%†
Kagi LLM BenchmarkKagi LLM Benchmark–80.1%
GPQA Diamond (HELM)HELM Capabilities–80.3%
ARC-AGI-1ARC Prize97.5%75.0%
ARC-AGI-2ARC Prize90.4%54.0%
ARC-AGI-3ARC Prize30.2%†–
CritPtArtificial Analysis29.1%9.1%†
MysteryMechanismVals AI37.4%†–
SciPredictScale AI SEAL–25.3%
Chess PuzzlesEpoch AI Benchmarking Hub43.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub59.0%–
CL-benchEpoch AI Benchmarking Hub–15.8%
LMCAEpoch AI Benchmarking Hub63.3%–
DTBenchEpoch AI Benchmarking Hub97.6%–
ForecastBenchForecastBench66.5%65.3%
BTF-3Epoch AI Benchmarking Hub12.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–72.9%
SciCodeSciCode56.4%–
Show all 173 benchmarks
MetricPublisherClaude Opus 5 (max)Gemini 3 Pro
Coding
WeirdMLWeirdML91.8%69.9%
FrontierCodeCognition53.4%–
GSO-BenchGSO-Bench–18.6%
Arena CodingArena (LMArena)15281517
Arena WebDevArena (LMArena)16911440
LiveBench 1.0 CodingLiveBench81.5%–
LiveCodeBenchVals AI89.0%†86.4%
IOIVals AI84.3%†–
SWE-bench (Vals)Vals AI97.0%†76.4%†
SWE-Bench ProScale AI SEAL–43.3%
SWE-bench Verified (bash only)SWE-bench–74.2%
SWE-bench Verified (any scaffold)SWE-bench–77.4%
Code MigrationVals AI57.5%†–
ProgramBenchVals AI3.0%†–
Vibe Code Bench 1-100Vals AI28.5%†–
Vibe Code Bench v1.1Vals AI88.4%†14.3%†
SWE-Bench Pro (private)Scale AI SEAL–43.3%
SWE Atlas: Codebase QnAScale AI SEAL63.2%†–
SWE Atlas: Test WritingScale AI SEAL62.2%†–
DeepSWE v1.1Epoch AI Benchmarking Hub73.7%–
CursorBenchCursor46.6%–
ALE-BenchEpoch AI Benchmarking Hub2164.6†1176.8
AlgoTuneAlgoTune–1.8
FrontierSWEEpoch AI Benchmarking Hub52.0%–
Terminal-Bench 4.0 (AA)Artificial Analysis49.0%–
Terminal-Bench 2.1 (AA)Artificial Analysis89.1%–
Startrise FrontendStartrise82.3%†–
Agents & tools
Terminal-BenchTerminal-Bench51.8%69.4%
OSWorld-Verified 2.0OSWorld31.4%–
GDPvalOpenAI–40.3%
Remote Labor IndexScale AI / CAIS–1.3%
APEX-AgentsMercor65.8%–
Arena AgentArena (LMArena)8.2–
LiveBench Agentic CodingLiveBench65.2%–
Terminal-Bench HardArtificial Analysis–41.7%†
τ²-Bench Telecom (AA)Artificial Analysis–87.1%†
Terminal-Bench 2.1 (Vals)Vals AI84.6%†–
MCP AtlasScale AI SEAL85.8%†70.3%
HiL-BenchScale AI SEAL57.0%†–
BFCL OverallBerkeley Function Calling Leaderboard–72.5%
τ²-benchτ²-bench–82.5%†
τ³-bench Bankingτ²-bench48.7%18.0%†
τ³-Banking (AA)Artificial Analysis42.1%–
Analyst Agent (AA)Artificial Analysis53.8%–
CUA-benchVals AI9.0%–
CyberBenchVals AI65.4%†–
Finance Agent v2Vals AI58.6%†–
Harvey's Legal Agent Benchmark v1Vals AI6.7%†–
Legal Research BenchVals AI55.3%†–
Poker AgentVals AI–1078.9%
SkillsBenchVals AI60.4%†–
SREBenchVals AI12.2%†–
Tax Agent BenchVals AI45.5%†–
Terminal-Bench 2.0 (Vals)Vals AI–55.1%†
Terminal-Bench 4.0 (Vals)Vals AI53.5%†–
Terminal-Bench ScienceVals AI27.1%†–
Time Horizon Index: KSPVals AI18.8%†–
Arena SearchArena (LMArena)1214†–
BALROGBALROG63.4%58.1%
DeepResearch BenchDeepResearch Bench–46.3%†
PostTrainBenchEpoch AI Benchmarking Hub35.0%†–
METR Time HorizonsMETR–71.0%
GBAEvalEpoch AI Benchmarking Hub79.6%†–
Vending-Bench 2Andon Labs11181.9†5478.2
AutomationBenchArtificial Analysis56.6%–
GDP.pdf (AA)Artificial Analysis21.6%–
EnterpriseOps-GymArtificial Analysis47.5%–
AA-Briefcase v1.1Artificial Analysis1657–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis28.6%–
DeepSec-Bench (AA)Artificial Analysis25.9%–
FACTS SearchGoogle85.3%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub85.6%–
FrontierMath Tier 4Epoch AI Benchmarking Hub73.2%–
OTIS Mock AIMEEpoch AI Benchmarking Hub98.9%91.4%
ProofBenchVals AI99.0%20.0%
LiveBench MathematicsLiveBench95.7%–
AIME (Vals)Vals AI–96.7%†
MGSMVals AI–93.9%†
AIME 2026MathArena–91.7%
HMMT February 2026MathArena–86.4%
MathArena ApexMathArena–23.4%
Omni-MATH (HELM)HELM Capabilities–55.6%
MATH 500Vals AI–96.4%†
Arena MathsArena (LMArena)15171477
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub59.9%–
LiveBench 1.0 Data AnalysisLiveBench74.5%–
AA-OmniscienceArtificial Analysis37.115.3†
MMLU-ProVals AI91.6%†90.1%
LegalBenchVals AI87.0%†87.0%†
CorpFinVals AI73.2%†63.7%†
TaxEvalVals AI75.1%†72.6%†
MedQAVals AI–96.0%†
PRBench FinanceScale AI SEAL–39.2%
PRBench LegalScale AI SEAL–40.6%
MultiNRCScale AI SEAL–59.0%
MMLU-Pro (HELM)HELM Capabilities–90.3%
BioMysteryBenchVals AI79.3%†–
CaseLaw v2Vals AI–53.1%†
Excel Modeling BenchmarkVals AI73.6%†–
MedCodeVals AI63.6%†52.2%†
MedScribeVals AI91.0%†72.0%†
Public Benefits Bench v1.1Vals AI76.9%†–
DrugDiscoveryBenchScale AI SEAL53.7%–
EBR-benchEpoch AI Benchmarking Hub45.7%–
GDP.pdfEpoch AI Benchmarking Hub24.0%–
AA-Omniscience: accuracyArtificial Analysis60.9%55.8%†
AA-Omniscience: non-hallucinationArtificial Analysis39.2%8.6%†
Global-MMLU-Lite (AA)Artificial Analysis–92.2%†
Instruction following
LiveBench LanguageLiveBench88.7%–
LiveBench Instruction FollowingLiveBench63.8%–
IFBenchArtificial Analysis–70.4%†
MultiChallengeScale AI SEAL–65.7%
TutorBenchScale AI SEAL–53.7%
IFEval (HELM)HELM Capabilities–87.6%
WildBench (HELM)HELM Capabilities–85.9%
Arena Instruction FollowingArena (LMArena)14951473
Human preference
Arena TextArena (LMArena)14911486
EQ-Bench 4EQ-Bench1360†–
Arena Creative WritingArena (LMArena)14741485
Arena Multi-turnArena (LMArena)14871496
Arena Longer QueriesArena (LMArena)15031491
Multimodal
Arena VisionArena (LMArena)1320†1305
MMMU-ProArtificial Analysis84.7%80.2%†
VISTAScale AI SEAL–51.5%
MMMU-Pro (official)MMMU–81.0%
MMMU-Pro (Vals)Vals AI89.9%†87.5%†
MortgageTaxVals AI72.1%†69.1%†
SAGEVals AI49.4%†47.6%†
AudioMCScale AI SEAL–54.6%†
AudioMC (text output)Scale AI SEAL–54.6%†
VTBScale AI SEAL–26.9%
GeoBenchGeoBench–84.0%
VPCTEpoch AI Benchmarking Hub–91.0%
Blueprint-Bench 2Epoch AI Benchmarking Hub30.4%†–
Long context
AA-LCRArtificial Analysis79.3%76.0%†
Arena DocumentArena (LMArena)1490†1451
MLCRArtificial Analysis11.1%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub163.9†153.1
LiveBench 1.0LiveBench80.1%–
AA Intelligence Index v4.3.2Artificial Analysis50.828.0†
HELM Capabilities meanHELM Capabilities–79.9%
Vals RSI IndexVals AI33.0%–
Vals Science IndexVals AI47.9%†–
Vals Multimodal IndexVals AI73.9%†–
Safety & honesty
FORTRESSScale AI SEAL16.8%†41.7%
MASKScale AI SEAL–42.6%
PropensityBenchScale AI SEAL–52.9%
Metadata
AA Openness IndexArtificial Analysis–5.6†

Data as of 2026-10-26. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Claude Opus 5 (max): 1 new result (Vals RSI Index).
  • Gemini 3 Pro: 1 score revision.
  • Claude Opus 5 (max): 1 score revision.
  • Claude Opus 5 (max): 1 new result (ForecastBench); 1 score revision.
  • Gemini 3 Pro: 1 score revision.
  • Claude Opus 5 (max): BenchLeader Index 68.3 → 68.9.
  • Claude Opus 5 (max): 4 new results (GDPval-AA v2.1, AA-Omniscience: accuracy, AA-Omniscience: non-hallucination…).
  • Claude Opus 5 (max): 1 score revision.
  • Claude Opus 5 (max): 2 score revisions.
  • Gemini 3 Pro: 1 new result (PRBench Legal).

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

Claude Opus 5 vs Gemini 3 Pro: questions

Is Claude Opus 5 better than Gemini 3 Pro?
Claude Opus 5 (max) leads on quality: 68.8 vs 60.4. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5 (max) is ahead overall as of 2026-10-26, but check the category scores for your use.
Is Claude Opus 5 better than Gemini 3 Pro for coding?
Claude Opus 5 scores higher in coding (70 vs 58 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1691 for Claude Opus 5 against 1440 for Gemini 3 Pro.
Is Claude Opus 5 better than Gemini 3 Pro for agents and tool use?
Claude Opus 5 scores higher in agentic tasks (64 vs 62 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 51.8% for Claude Opus 5 against 69.4% for Gemini 3 Pro.
Do independent benchmarks agree on Claude Opus 5 vs Gemini 3 Pro?
Across the 17 benchmarks both have, Claude Opus 5 leads 14, Gemini 3 Pro leads 3. Every overall index that rates both puts Claude Opus 5 ahead.
When was Claude Opus 5 released?
Claude Opus 5 was released on 24 Jul 2026.