BenchLeader

Claude Opus 5.5 vs Gemini 2.5 Pro Preview 0325

Full profiles: Claude Opus 5.5 (Anthropic) and Gemini 2.5 Pro Preview 0325 (Google): every benchmark, price and rank.

Updated · Data from 15 sources

As of 22 Nov 2026, Claude Opus 5.5 is ahead of Gemini 2.5 Pro Preview 0325 on quality (67.7 vs 59.7 on the BenchLeader Index). Choose Claude Opus 5.5 for reasoning (71 vs 52), coding (78 vs 61), and knowledge (71 vs 56); choose Gemini 2.5 Pro Preview 0325 for long context (73 vs 67) and multimodal (71 vs 70).

Key facts (as of 22 Nov 2026)

  • Claude Opus 5.5 scores 67.7 on the BenchLeader Index and Gemini 2.5 Pro Preview 0325 scores 59.7 (BenchLeader, 22 Nov 2026).
  • Claude Opus 5.5 costs $8.00 per 1M tokens blended (list price, 22 Nov 2026).
  • Of the 4 benchmarks both models have, Claude Opus 5.5 leads 4 (BenchLeader, 22 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 5.578 vs 61 category scoreHigh
MathsClaude Opus 5.573 vs 59 category scoreHigh
ReasoningClaude Opus 5.571 vs 52 category score; GPQA Diamond 90.6% vs 83.8%High
KnowledgeClaude Opus 5.571 vs 56 category scoreHigh
Long documentsGemini 2.5 Pro Preview 032573 vs 67 category scoreMedium
Images and other mediaGemini 2.5 Pro Preview 032571 vs 70 category scoreMedium
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Opus 5.5 (max) leads on quality: 67.7 vs 59.7.
  • Claude Opus 5.5 (max) is stronger in coding, knowledge, maths, reasoning.
  • Gemini 2.5 Pro Preview 0325 is stronger in long context, multimodal.

At a glance

SpecClaude Opus 5.5Gemini 2.5 Pro Preview 0325
DeveloperAnthropicGoogle
Released22 Sep 202625 Mar 2025
Context window (tokens)1,000,0001,000,000
Max output (tokens)128,000 (up to 300K on the Message Batches API (beta))–
Input typestext, image–
Reasoning effort settingslow, medium, high, xhigh, max–
Compared atClaude Opus 5.5 (max)Gemini 2.5 Pro Preview 0325
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / $0.200–
API model IDclaude-opus-5-5–
Where to use itClaude API, Amazon Bedrock, Google Cloud, Microsoft Foundry–

Limits, availability and announced prices from the vendors' own pages: platform.claude.com (checked 20 Oct 2026). Everything else is from the day's data.

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 5.5 (max)Gemini 2.5 Pro Preview 0325Leader
Reasoning70.652.1Claude Opus 5.5
Coding77.561.1Claude Opus 5.5
Agents & tools63.7–not comparable
Maths72.658.9Claude Opus 5.5
Knowledge71.156.2Claude Opus 5.5
Instruction following–57.9not comparable
Multimodal69.870.8Gemini 2.5 Pro Preview 0325
Long context67.172.8Gemini 2.5 Pro Preview 0325
Composite68.0–not 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 avg75ReasoningCodingMathsKnowledgeLong contextMultimodalClaude Opus 5.5, Reasoning: 70.6Claude Opus 5.5, Coding: 77.5Claude Opus 5.5, Maths: 72.6Claude Opus 5.5, Knowledge: 71.1Claude Opus 5.5, Long context: 67.1Claude Opus 5.5, Multimodal: 69.8Gemini 2.5 Pro Preview 0325, Reasoning: 52.1Gemini 2.5 Pro Preview 0325, Coding: 61.1Gemini 2.5 Pro Preview 0325, Maths: 58.9Gemini 2.5 Pro Preview 0325, Knowledge: 56.2Gemini 2.5 Pro Preview 0325, Long context: 72.8Gemini 2.5 Pro Preview 0325, Multimodal: 70.8

Not drawn, measured for fewer than two of these models: Agents & tools, Instruction following, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 4 benchmarks both have, Claude Opus 5.5 leads 4, Gemini 2.5 Pro Preview 0325 leads 0. Every overall index that rates both puts Claude Opus 5.5 ahead.

Overall indexClaude Opus 5.5 (max)Gemini 2.5 Pro Preview 0325Leader
BenchLeader Index67.759.7Claude Opus 5.5

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 5.5 (max)Gemini 2.5 Pro Preview 0325
Blended price per 1M tokens$8.00–
Input / output per 1M$4.00 / $20.00– / –
Cached input per 1M$0.200–
Price per task: chat reply$0.0076–
Price per task: summarize a 30-page report$0.060–
Price per task: code edit$0.054–
Price per task: agentic coding session$0.320–
Price per task: structured extraction$0.012–
Agentic coding session, input mostly cached$0.149–
Cost per benchmark task (AA Index)$10.04–
Output tokens per task (AA Index)173k–
Of which reasoning120k–
Time per task (AA Index)25 min–
Output speed114 tok/s–
Time to first answer345.4 s–
Time to a complete answer, last measured 13 Nov 2026711.4 s–

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5.5 (max) scores 67.7 and takes 345 s to its first answer token; Claude Opus 5.5 (high) scores 65.5 in 24 s, Claude Opus 5.5 (xhigh) scores 64.4 in 69 s. Gemini 2.5 Pro Preview 0325 scores 59.7. 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

199 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 5.5 (max)Gemini 2.5 Pro Preview 0325
BenchLeader IndexBenchLeader67.759.7
Agents & tools scoreBenchLeader63.7–
Coding scoreBenchLeader77.561.1
Composite scoreBenchLeader68.0–
Knowledge scoreBenchLeader71.156.2
Long context scoreBenchLeader67.172.8
Maths scoreBenchLeader72.658.9
Multimodal scoreBenchLeader69.870.8
Reasoning scoreBenchLeader70.652.1
Instruction following scoreBenchLeader–57.9
Blended price $/MBenchLeader$8.00–
Output speedBenchLeader114 tok/s–
Time to first answerBenchLeader345.4 s–
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.6%83.8%
Humanity's Last ExamScale AI / CAIS–18.2%
SimpleBenchSimpleBench88.4%†51.6%
Arena Hard PromptsArena (LMArena)1530†–
LiveBench 2.0 ReasoningLiveBench92.2%–
LiveBench 1.0 ReasoningLiveBench92.2%–
GPQA Diamond (AA)Artificial Analysis–83.6%
Humanity's Last Exam (AA)Artificial Analysis61.4%18.0%
HLE-Diamond (AA)Artificial Analysis67.9%–
GPQA Diamond (Vals)Vals AI–80.8%
GPQA Diamond (HELM)HELM Capabilities–74.9%
ARC-AGI-1ARC Prize97.5%–
ARC-AGI-2ARC Prize91.7%–
CritPtArtificial Analysis31.7%–
CritPt v2 hard subset (AA)Artificial Analysis68.0%–
MysteryMechanismVals AI49.5%–
HLE-Diamond (Scale)Scale AI SEAL55.0%†–
HLE Text-Only (Scale)Scale AI SEAL–18.4%
Arena ExpertArena (LMArena)1549†–
Chess PuzzlesEpoch AI Benchmarking Hub67.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub71.0%–
LMCAEpoch AI Benchmarking Hub68.2%–
DTBenchEpoch AI Benchmarking Hub98.9%–
ForecastBenchForecastBench66.6%†64.0%
Coding
SciCodeSciCode66.9%–
Show all 199 benchmarks
MetricPublisherClaude Opus 5.5 (max)Gemini 2.5 Pro Preview 0325
Coding
FrontierCodeCognition54.6%†–
Arena CodingArena (LMArena)1548†–
Arena WebDevArena (LMArena)1819–
LiveBench 2.0 CodingLiveBench87.1%–
LiveBench 1.0 CodingLiveBench89.3%–
LiveCodeBenchVals AI–79.2%
IOIVals AI95.1%–
Aider PolyglotAider polyglot leaderboard–72.9%
Code MigrationVals AI66.7%–
Code Migration v1.1Vals AI81.0%–
ProgramBenchVals AI18.5%–
SWE-bench MultimodalVals AI70.2%–
Vibe Code Bench 1-100Vals AI30.4%†–
Vibe Code Bench v1.1Vals AI90.3%–
Vibe Code Bench 1-100 v1.1Vals AI30.9%–
SWE Atlas v1.1Scale AI SEAL77.5%–
SWE Atlas v1.1: Codebase QnAScale AI SEAL77.4%–
SWE Atlas v1.1: Test WritingScale AI SEAL77.8%–
SWE Atlas v1.1: RefactoringScale AI SEAL77.1%–
MirrorCodeEpoch AI Benchmarking Hub95.6%–
CadEvalEpoch AI Benchmarking Hub–64.0%
CursorBenchCursor58.1%–
ALE-BenchEpoch AI Benchmarking Hub2147.4†–
FrontierSWEEpoch AI Benchmarking Hub62.3%–
WeirdML v3WeirdML31.2%†–
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%–
Startrise FrontendStartrise80.2%†–
GameBench 2 OverallDuelLab GameBench 287.6†–
GameBench 2 by reasoning settingDuelLab GameBench 294.8†–
Design Arena WebsiteDesign Arena1322†–
Design Arena CodeDesign Arena1382†–
FrontierCode 1.1 (AA)Artificial Analysis52.2%–
FrontierCode 2.0 (AA)Artificial Analysis46.4%–
LiveCodeBench (AA)Artificial Analysis–77.8%
Agents & tools
Terminal-BenchTerminal-Bench65.8%–
Remote Labor IndexScale AI / CAIS21.3%†–
APEX-AgentsMercor73.5%–
Arena AgentArena (LMArena)18.6–
LiveBench Long AgenticLiveBench72.8%–
LiveBench BrowserLiveBench88.4%–
LiveBench Agentic CodingLiveBench71.7%–
Terminal-Bench 2.1 (Vals)Vals AI87.6%†–
MCP AtlasScale AI SEAL85.4%†–
HiL-BenchScale AI SEAL59.0%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis68.3%–
GDPval-AA v2.1Artificial Analysis1866–
ITBench SRE (AA)Artificial Analysis38.2%–
Analyst Agent (AA)Artificial Analysis56.3%–
CUA-benchVals AI14.0%–
CyberBenchVals AI55.4%–
Finance Agent v2Vals AI58.6%–
Finance Agent v2.1Vals AI67.8%–
Harvey's Legal Agent Benchmark v1.1Vals AI9.2%–
Harvey's Legal Agent Benchmark v1Vals AI3.8%–
Legal Research BenchVals AI50.5%–
Robo-benchVals AI14.6%–
SREBenchVals AI33.6%–
Tax Agent BenchVals AI44.5%–
Terminal-Bench 4.0 (Vals)Vals AI65.2%–
Terminal-Bench ScienceVals AI47.1%–
Time Horizon Index: KSPVals AI91.3%–
Web Search IndexVals AI53.8%–
Arena SearchArena (LMArena)1213†–
Arena Agent Task CompletionArena (LMArena)19.2–
Arena Search FactualityArena (LMArena)1207†–
BALROGBALROG–43.3%
PostTrainBenchEpoch AI Benchmarking Hub43.8%–
GBAEvalEpoch AI Benchmarking Hub90.6%†–
Vending-Bench 2Andon Labs9235.3†–
SpireClimbEpoch AI Benchmarking Hub5.8%–
AutomationBenchArtificial Analysis69.5%–
GDP.pdf (AA)Artificial Analysis26.2%–
Harvey LAB-AA v1.1Harvey4.2%–
AA-Briefcase v1.1Artificial Analysis1797–
GDPxGDPx by SemiAnalysis11.9%–
Design Arena AgenticDesign Arena1322†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis59.0%–
CWE-Bench (AA)Artificial Analysis58.3%–
DeepSec-Bench (AA)Artificial Analysis26.9%–
CyberGym end-to-end (AA)Artificial Analysis0.8%–
MKA (AA)Artificial Analysis53.0%–
FACTS SearchGoogle88.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub91.2%–
FrontierMath Tier 4Epoch AI Benchmarking Hub95.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
MATH Level 5Epoch AI Benchmarking Hub–95.6%
ProofBenchVals AI100.0%–
LiveBench MathematicsLiveBench97.1%–
AIME (Vals)Vals AI–85.8%
ArXivMathMathArena82.6%†–
BrokenArXivMathArena77.3%†–
Omni-MATH (HELM)HELM Capabilities–41.6%
MATH 500Vals AI–95.2%
Arena MathsArena (LMArena)1517†–
FrontierMath ErdősEpoch AI Benchmarking Hub2.9%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub72.2%–
LiveBench 2.0 Data AnalysisLiveBench80.3%–
LiveBench ResearchLiveBench88.9%–
LiveBench 1.0 Data AnalysisLiveBench80.3%–
AA-Omniscience v1.1Artificial Analysis48.1–
MMLU-ProVals AI–84.1%
LegalBenchVals AI–84.3%
CorpFinVals AI–59.8%
TaxEvalVals AI–72.9%
MedQAVals AI–93.1%
PRBench LegalScale AI SEAL47.6%†–
MMLU-Pro (HELM)HELM Capabilities–86.3%
BioMysteryBenchVals AI79.3%–
ClaimBenchVals AI100.0%–
Excel Modeling BenchmarkVals AI75.9%–
Excel Modeling Benchmark v1.1Vals AI75.8%–
MedCodeVals AI49.8%–
MedScribeVals AI91.4%–
Public Benefits Bench v1.1Vals AI70.6%–
Access to Justice BenchmarkVals AI73.8%–
Financial Coaching BenchVals AI76.2%–
Immigration BenchVals AI72.1%–
Arena Text FactualityArena (LMArena)1505†–
EBR-benchEpoch AI Benchmarking Hub71.4%–
GDP.pdfEpoch AI Benchmarking Hub48.8%–
AA-Omniscience v1.1: accuracyArtificial Analysis65.5%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis49.7%–
HealthBench Professional (AA)OpenAI59.9%–
FACTS ParametricGoogle58.7%†–
Instruction following
LiveBench LanguageLiveBench86.3%–
LiveBench Instruction FollowingLiveBench65.7%–
IFEval (HELM)HELM Capabilities–84.0%
WildBench (HELM)HELM Capabilities–85.7%
Arena Instruction FollowingArena (LMArena)1516†–
Human preference
Arena TextArena (LMArena)1506†–
EQ-Bench 4EQ-Bench1340†–
EQ-Bench Creative Writing v3EQ-Bench2051†1396
EQ-Bench Longform WritingEQ-Bench84.6†58.8
Arena Creative WritingArena (LMArena)1516†–
Arena Multi-turnArena (LMArena)1501†–
Arena Longer QueriesArena (LMArena)1520†–
Lech Mazur Creative WritingLech Mazur–80.5%
Multimodal
Arena VisionArena (LMArena)1322†–
LiveBench DesignLiveBench83.3%–
MMMU-ProArtificial Analysis87.7%–
VISTAScale AI SEAL–54.6%
MMMU-Pro (Vals)Vals AI–81.3%
MortgageTaxVals AI–67.2%
SAGEVals AI91.3%–
Humanity's Sixth SenseScale AI SEAL44.6%†–
GeoBenchGeoBench–84.0%
VPCTEpoch AI Benchmarking Hub–48.0%
Blueprint-Bench 2Epoch AI Benchmarking Hub51.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub83.3%–
VIALS-AAHandshake AI61.5%–
Code2Video-AAArtificial Analysis1536–
AA-3DArtificial Analysis1202–
FACTS MultimodalGoogle56.4%†–
Long context
Fiction.LiveBench 120kFiction.live–90.6%
AA-LCR v1.1Artificial Analysis84.7%–
MLCRArtificial Analysis27.8%–
FACTS GroundingGoogle62.5%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.7†144.0
LiveBench 2.0LiveBench83.4%–
LiveBench 1.0LiveBench83.2%–
AA Intelligence Index v5.0.1Artificial Analysis59.1–
AA Intelligence Index v4.3.2Artificial Analysis57.615.0
AA Progress Index v1Artificial Analysis350245.9
Vals IndexVals AI70.1–
HELM Capabilities meanHELM Capabilities–74.5%
Vals Finance IndexVals AI65.3%–
Vals RSI IndexVals AI37.3%–
Vals Science IndexVals AI58.6%–
Vals Router IndexVals AI64.2%†–
Vals Legal IndexVals AI72.4%–
AA Cyber IndexArtificial Analysis28.7–
Safety & honesty
FORTRESSScale AI SEAL5.8%54.9%
MASKScale AI SEAL–55.9%
DistressBenchScale AI SEAL75.6%†–

Data as of 2026-11-22. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261119-1d7fd529faf6 (https://benchmarks.duellab.org/releases/gb2-20261119-1d7fd529faf6/), 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 5.5 (max): 4 new results (SWE Atlas v1.1, SWE Atlas v1.1: Codebase QnA, SWE Atlas v1.1: Test Writing…); 1 score revision.
  • Claude Opus 5.5 (max): BenchLeader Index 68.3 → 67.6.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 5.5 (max): BenchLeader Index 68.8 → 68.3.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 38 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • Claude Opus 5.5 (max): 1 new result (PostTrainBench); 1 score revision.
  • Claude Opus 5.5 (max): 1 new result (MirrorCode); 1 score revision.
  • Claude Opus 5.5 (max): BenchLeader Index 69.3 → 68.8.
  • Claude Opus 5.5 (max): 2 score revisions.

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

Claude Opus 5.5 vs Gemini 2.5 Pro Preview 0325: questions

Is Claude Opus 5.5 better than Gemini 2.5 Pro Preview 0325?
Claude Opus 5.5 (max) leads on quality: 67.7 vs 59.7. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5.5 (max) is ahead overall as of 22 Nov 2026, but check the category scores for your use.
Is Claude Opus 5.5 or Gemini 2.5 Pro Preview 0325 better for coding?
Claude Opus 5.5 scores higher in coding (78 vs 61 on the category index, where 50 is average).
Which is better for long documents?
Gemini 2.5 Pro Preview 0325 scores higher on long-context benchmarks (73 vs 67). Both accept 1,000,000 tokens of context.
Do independent benchmarks agree on Claude Opus 5.5 vs Gemini 2.5 Pro Preview 0325?
Across the 4 benchmarks both have, Claude Opus 5.5 leads 4, Gemini 2.5 Pro Preview 0325 leads 0. Every overall index that rates both puts Claude Opus 5.5 ahead.
When was Claude Opus 5.5 released?
Claude Opus 5.5 was released on 22 Sep 2026.