BenchLeader

Claude Sonnet 5.5 vs Gemini 3.1 Pro

Full profiles: Claude Sonnet 5.5 (Anthropic) and Gemini 3.1 Pro (Google): every benchmark, price and rank.

Updated · Data from 15 sources

As of 12 Nov 2026, Claude Sonnet 5.5 is ahead of Gemini 3.1 Pro on quality (64.7 vs 60.5 on the BenchLeader Index), and they cost about the same at $4.00 vs $4.50 per 1M tokens blended. Choose Claude Sonnet 5.5 for agents & tools (70 vs 57), coding (72 vs 59), and maths (71 vs 66), where it also streams faster; choose Gemini 3.1 Pro for fast first answers (14.5 s vs 245.2 s) and knowledge (66 vs 58).

Key facts (as of 12 Nov 2026)

  • Claude Sonnet 5.5 scores 64.7 on the BenchLeader Index and Gemini 3.1 Pro scores 60.5 (BenchLeader, 12 Nov 2026).
  • Claude Sonnet 5.5 costs $4.00 per 1M tokens blended (list price, 12 Nov 2026).
  • Gemini 3.1 Pro costs $4.50 per 1M tokens blended (list price, 12 Nov 2026).
  • Claude Sonnet 5.5 streams faster than Gemini 3.1 Pro (Artificial Analysis, 7-day median, 12 Nov 2026).
  • Of the 17 benchmarks both models have, Claude Sonnet 5.5 leads 12 (BenchLeader, 12 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 Sonnet 5.572 vs 59 category score; LiveBench 1.0 Coding 91.4% vs 76.5%High
Agents & tool useClaude Sonnet 5.570 vs 57 category score; LiveBench Agentic Coding 56.3% vs 44.1%High
MathsClaude Sonnet 5.571 vs 66 category score; OTIS Mock AIME 100.0% vs 95.6%Medium
ReasoningClaude Sonnet 5.568 vs 65 category score; GPQA Diamond 95.6% vs 94.4%Medium
KnowledgeGemini 3.1 Pro66 vs 58 category score; SimpleQA Verified 73.5% vs 46.5%High
Lowest costEither$4.00 vs $4.50 per 1M blended; agentic coding session $0.160 vs $0.168–
Fastest first answerGemini 3.1 Pro14.5 s (Gemini 3.1 Pro (high)) vs 245.2 s (Claude Sonnet 5.5 (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 Sonnet 5.5 (max) leads on quality: 64.7 vs 60.5.
  • Claude Sonnet 5.5 (max) is stronger in agents & tools, coding, maths, reasoning.
  • Gemini 3.1 Pro (high) is stronger in knowledge.
  • They cost about the same ($4.00 per 1M blended).
  • Claude Sonnet 5.5 (max) streams 1.3× faster (146 vs 112 tokens per second).

At a glance

SpecClaude Sonnet 5.5Gemini 3.1 Pro
DeveloperAnthropicGoogle
Released28 Sep 202619 Feb 2026
Context window (tokens)1,000,0001,048,576
Compared atClaude Sonnet 5.5 (max)Gemini 3.1 Pro (high)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.100$2.00 / $12.00 / $0.200

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 Sonnet 5.5 (max)Gemini 3.1 Pro (high)Leader
Reasoning68.164.7Claude Sonnet 5.5
Coding71.558.6Claude Sonnet 5.5
Agents & tools69.956.7Claude Sonnet 5.5
Maths71.365.9Claude Sonnet 5.5
Knowledge57.665.6Gemini 3.1 Pro
Long context66.1–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 avg75ReasoningCodingAgents & toolsMathsKnowledgeClaude Sonnet 5.5, Reasoning: 68.1Claude Sonnet 5.5, Coding: 71.5Claude Sonnet 5.5, Agents & tools: 69.9Claude Sonnet 5.5, Maths: 71.3Claude Sonnet 5.5, Knowledge: 57.6Gemini 3.1 Pro, Reasoning: 64.7Gemini 3.1 Pro, Coding: 58.6Gemini 3.1 Pro, Agents & tools: 56.7Gemini 3.1 Pro, Maths: 65.9Gemini 3.1 Pro, Knowledge: 65.6

Not drawn, measured for fewer than two of these models: Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 17 benchmarks both have, Claude Sonnet 5.5 leads 12, Gemini 3.1 Pro leads 5. Independent sources split: Claude Sonnet 5.5 leads on BenchLeader Index; Gemini 3.1 Pro leads on Arena Text.

Overall indexClaude Sonnet 5.5 (max)Gemini 3.1 Pro (high)Leader
BenchLeader Index64.760.5Claude Sonnet 5.5
Arena Text1473†1487Gemini 3.1 Pro

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 Sonnet 5.5 (max)Gemini 3.1 Pro (high)
Blended price per 1M tokens$4.00$4.50
Input / output per 1M$2.00 / $10.00$2.00 / $12.00
Cached input per 1M$0.100$0.200
Price per task: chat reply$0.0038$0.0044
Price per task: summarize a 30-page report$0.030$0.031
Price per task: code edit$0.027$0.030
Price per task: agentic coding session$0.160$0.168
Price per task: structured extraction$0.0060$0.0064
Agentic coding session, input mostly cached$0.074$0.087
Cost per benchmark task (AA Index)$10.02–
Output tokens per task (AA Index)285k–
Of which reasoning206k–
Time per task (AA Index)33 min–
Output speed146 tok/s112 tok/s
Time to first answer245.2 s14.5 s
Time to a complete answer480.4 s36.4 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 5.5 (max) scores 64.7 and takes 245 s to its first answer token; Claude Sonnet 5.5 (xhigh) scores 62.7 in 29 s, Claude Sonnet 5.5 (high) scores 58.1 in 11 s. Gemini 3.1 Pro (high) scores 60.5 and takes 15 s to its first answer token; Gemini 3.1 Pro scores 59.9 in 15 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

186 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 Sonnet 5.5 (max)Gemini 3.1 Pro (high)
BenchLeader IndexBenchLeader64.760.5
Agents & tools scoreBenchLeader69.956.7
Coding scoreBenchLeader71.558.6
Knowledge scoreBenchLeader57.665.6
Long context scoreBenchLeader66.1–
Maths scoreBenchLeader71.365.9
Reasoning scoreBenchLeader68.164.7
Blended price $/MBenchLeader$4.00$4.50
Output speedBenchLeader146 tok/s112 tok/s
Time to first answerBenchLeader245.2 s14.5 s
Context windowBenchLeader1,000,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub95.6%94.4%
Humanity's Last ExamScale AI / CAIS46.1%†46.4%†
SimpleBenchSimpleBench75.9%†79.6%†
Arena Hard PromptsArena (LMArena)1498†1507†
LiveBench 2.0 ReasoningLiveBench91.6%†–
LiveBench 1.0 ReasoningLiveBench91.6%84.0%
GPQA Diamond (AA)Artificial Analysis–94.1%†
Humanity's Last Exam (AA)Artificial Analysis55.0%47.0%†
HLE-Diamond (AA)Artificial Analysis53.3%31.4%†
GPQA Diamond (Vals)Vals AI–95.5%
EnigmaEvalScale AI SEAL–36.8%
ARC-AGI-1ARC Prize96.5%98.0%†
ARC-AGI-2ARC Prize83.9%†77.1%†
ARC-AGI-3ARC Prize72.4%†0.4%†
CritPtArtificial Analysis31.4%17.7%†
CritPt v2 hard subset (AA)Artificial Analysis59.0%–
MysteryMechanismVals AI49.1%†20.7%
Chess PuzzlesEpoch AI Benchmarking Hub59.0%51.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub65.0%34.0%
CL-benchEpoch AI Benchmarking Hub–20.8%†
CL-bench LifeEpoch AI Benchmarking Hub–16.9%†
LMCAEpoch AI Benchmarking Hub68.3%53.8%
DTBenchEpoch AI Benchmarking Hub97.3%95.5%
ForecastBenchForecastBench–65.2%
Coding
SciCodeSciCode61.0%58.7%†
Show all 186 benchmarks
MetricPublisherClaude Sonnet 5.5 (max)Gemini 3.1 Pro (high)
Coding
WeirdMLWeirdML–72.1%†
FrontierCodeCognition52.1%†–
GSO-BenchGSO-Bench–22.6%†
Arena CodingArena (LMArena)1516†1520†
Arena WebDevArena (LMArena)1773†1447†
LiveBench 2.0 CodingLiveBench77.2%†–
LiveBench 1.0 CodingLiveBench91.4%76.5%
LiveCodeBenchVals AI–88.5%
IOIVals AI83.1%†51.8%
SWE-bench (Vals)Vals AI–78.8%
SWE-Bench ProScale AI SEAL–46.1%†
Code MigrationVals AI69.8%†17.3%
Code Migration v1.1Vals AI86.9%†–
ProgramBenchVals AI6.5%†0.0%
SWE-bench MultimodalVals AI58.3%†–
Vibe Code Bench 1-100Vals AI–6.7%
Vibe Code Bench v1.1Vals AI92.4%†32.0%
SWE-Bench Pro (private)Scale AI SEAL–46.1%†
SWE Atlas: Codebase QnAScale AI SEAL–13.5%†
SWE Atlas: RefactoringScale AI SEAL–33.8%†
SWE Atlas: Test WritingScale AI SEAL–29.8%†
MirrorCodeEpoch AI Benchmarking Hub97.8%8.9%
DeepSWE v1.1Epoch AI Benchmarking Hub–11.7%†
CursorBenchCursor55.5%–
ALE-BenchEpoch AI Benchmarking Hub1819.1†1160.6†
AlgoTuneAlgoTune–2.0†
FrontierSWEEpoch AI Benchmarking Hub61.9%–
Terminal-Bench 4.0 (AA)Artificial Analysis63.6%4.0%†
Terminal-Bench 2.1 (AA)Artificial Analysis–73.8%†
Startrise FrontendStartrise75.9%†–
GameBench 2 OverallDuelLab GameBench 260.3†–
GameBench 2 by reasoning settingDuelLab GameBench 291.2†–
Design Arena WebsiteDesign Arena1313†1229†
FrontierCode 1.1 (AA)Artificial Analysis45.8%–
FrontierCode 2.0 (AA)Artificial Analysis41.7%–
Agents & tools
Terminal-BenchTerminal-Bench63.9%80.2%†
APEX-AgentsMercor75.5%35.1%†
Arena AgentArena (LMArena)16-4.5†
LiveBench Long AgenticLiveBench63.4%†–
LiveBench BrowserLiveBench89.3%†–
LiveBench Agentic CodingLiveBench56.3%44.1%
Terminal-Bench HardArtificial Analysis–53.8%†
τ²-Bench Telecom (AA)Artificial Analysis–95.6%†
Terminal-Bench 2.1 (Vals)Vals AI83.2%†70.8%
MCP AtlasScale AI SEAL–78.2%
HiL-BenchScale AI SEAL–35.3%†
τ³-bench Bankingτ²-bench–26.0%
GDPval-AA v2.1, normalised scoreArtificial Analysis66.9%14.6%†
GDPval-AA v2.1Artificial Analysis1838799†
τ³-Banking (AA)Artificial Analysis–21.4%†
ITBench SRE (AA)Artificial Analysis–30.3%†
Analyst Agent (AA)Artificial Analysis57.5%41.3%†
APEX-Agents (AA)Artificial Analysis–32.0%†
CyberBenchVals AI59.6%†–
Finance Agent v2Vals AI58.1%†43.0%
Finance Agent v2.1Vals AI67.3%†–
Harvey's Legal Agent Benchmark v1.1Vals AI10.4%†–
Harvey's Legal Agent Benchmark v1Vals AI2.9%†0.0%
Legal Research BenchVals AI48.1%†20.7%
SREBenchVals AI30.1%†0.0%
Tax Agent BenchVals AI42.0%†9.3%
Terminal-Bench 2.0 (Vals)Vals AI–67.4%
Terminal-Bench 4.0 (Vals)Vals AI64.1%†2.5%
Terminal-Bench ScienceVals AI47.1%†1.4%
Arena SearchArena (LMArena)–1209†
BALROGBALROG–57.0%†
DeepResearch BenchDeepResearch Bench–47.8%
PostTrainBenchEpoch AI Benchmarking Hub–18.1%†
ExploitBenchEpoch AI Benchmarking Hub–26.1%†
METR Time HorizonsMETR–77.0%†
GBAEvalEpoch AI Benchmarking Hub–0.8%†
Vending-Bench 2Andon Labs11165.3†911.2†
AutomationBenchArtificial Analysis71.8%35.4%†
GDP.pdf (AA)Artificial Analysis25.8%17.8%†
Harvey LAB-AA v1.1Harvey2.8%0.0%†
EnterpriseOps-GymArtificial Analysis–42.2%†
AA-Briefcase v1.1Artificial Analysis1816457†
GDPxGDPx by SemiAnalysis8.2%–
Design Arena AgenticDesign Arena1281†1081†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis53.3%–
BrowseCompOpenAI–31.2%†
DeepSearchQAGoogle–60.2%†
FACTS SearchGoogle86.8%†90.2%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub88.8%59.6%†
FrontierMath Tier 4Epoch AI Benchmarking Hub80.5%26.8%†
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%95.6%
ProofBenchVals AI100.0%26.0%†
LiveBench MathematicsLiveBench96.1%91.0%
AIME (Vals)Vals AI–98.1%
AIME 2026MathArena–98.3%
HMMT February 2026MathArena–94.7%
USAMO 2026MathArena–74.4%
MathArena ApexMathArena–60.9%
Arena MathsArena (LMArena)1490†1488†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub46.5%73.5%
LiveBench 2.0 Data AnalysisLiveBench59.5%†–
LiveBench ResearchLiveBench88.0%†–
LiveBench 1.0 Data AnalysisLiveBench59.5%78.5%
AA-Omniscience v1.1Artificial Analysis30.5–
MMLU-ProVals AI–91.0%
LegalBenchVals AI–87.4%
CorpFinVals AI–64.5%
TaxEvalVals AI–72.9%
MedQAVals AI–96.4%
PRBench FinanceScale AI SEAL–41.9%†
PRBench LegalScale AI SEAL–44.0%†
MultiNRCScale AI SEAL–64.7%†
BioMysteryBenchVals AI81.1%†60.0%
CaseLaw v2Vals AI–64.8%
ClaimBenchVals AI100.0%†–
Excel Modeling BenchmarkVals AI75.7%†52.6%
Excel Modeling Benchmark v1.1Vals AI75.9%†–
MedCodeVals AI52.9%†59.1%
MedScribeVals AI91.1%†76.1%
Public Benefits Bench v1.1Vals AI67.2%†53.8%
DrugDiscoveryBenchScale AI SEAL–41.9%
EBR-benchEpoch AI Benchmarking Hub–14.3%†
GDP.pdfEpoch AI Benchmarking Hub31.4%17.0%
AA-Omniscience v1.1: accuracyArtificial Analysis51.5%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis56.7%–
Global-MMLU-Lite (AA)Artificial Analysis–93.2%†
HealthBench Professional (AA)OpenAI63.0%–
Instruction following
LiveBench LanguageLiveBench78.0%85.4%
LiveBench Instruction FollowingLiveBench56.8%79.1%
IFBenchArtificial Analysis–77.1%†
MultiChallengeScale AI SEAL–71.4%†
TutorBenchScale AI SEAL–53.0%†
Arena Instruction FollowingArena (LMArena)1480†1480†
Human preference
Arena TextArena (LMArena)1473†1487†
EQ-Bench 4EQ-Bench–1132†
Arena Creative WritingArena (LMArena)1465†1482†
Arena Multi-turnArena (LMArena)1469†1495†
Arena Longer QueriesArena (LMArena)1489†1499†
Multimodal
Arena VisionArena (LMArena)1284†1296†
LiveBench DesignLiveBench81.3%†–
MMMU-ProArtificial Analysis–82.4%†
MMMU-Pro (official)MMMU–80.5%
MMMU-Pro (Vals)Vals AI–88.2%
MortgageTaxVals AI–69.4%
SAGEVals AI88.0%†83.2%
VTBScale AI SEAL–29.0%†
GeoBenchGeoBench–84.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub39.3%†26.5%†
Code2Video-AAArtificial Analysis1443–
AA-3DArtificial Analysis1204–
Long context
AA-LCR v1.1Artificial Analysis82.7%82.0%†
Arena DocumentArena (LMArena)–1459†
MLCRArtificial Analysis41.7%11.1%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub166.6†156.2†
LiveBench 2.0LiveBench77.0%†–
LiveBench 1.0LiveBench75.7%77.0%
AA Intelligence Index v5.0Artificial Analysis54.5–
AA Intelligence Index v4.3.2Artificial Analysis5629.7†
AA Progress Index v1Artificial Analysis350.5296.1†
Vals IndexVals AI70.8†–
Vals Finance IndexVals AI64.5%†–
Vals Science IndexVals AI59.1%†27.4%
Vals Multimodal IndexVals AI–56.1%
Vals Router IndexVals AI69.0%†–
Safety & honesty
FORTRESSScale AI SEAL–29.8%†
MASKScale AI SEAL–42.4%†

Data as of 2026-11-12. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 3.1 Pro (high): 4 new results (AIME 2026, HMMT February 2026, USAMO 2026…).
  • Claude Sonnet 5.5 (max): 1 new result (MirrorCode).
  • Claude Sonnet 5.5 (max): 2 score revisions.
  • Claude Sonnet 5.5 (max): 1 score revision.
  • Claude Sonnet 5.5 (max): 1 score revision.
  • Claude Sonnet 5.5 (max): 1 score revision.
  • Claude Sonnet 5.5 (max): 1 new result (MirrorCode).
  • Claude Sonnet 5.5 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $5.46/M to $10.02/M (83% up).
  • Gemini 3.1 Pro (high): 1 score revision.
  • Gemini 3.1 Pro (high): cost per task moved from $1.30/M to $1.44/M (11% up).

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

Claude Sonnet 5.5 vs Gemini 3.1 Pro: questions

Is Claude Sonnet 5.5 better than Gemini 3.1 Pro?
Claude Sonnet 5.5 (max) leads on quality: 64.7 vs 60.5. The BenchLeader Index combines every independent quality benchmark; Claude Sonnet 5.5 (max) is ahead overall as of 12 Nov 2026, but check the category scores for your use.
Claude Sonnet 5.5 vs Gemini 3.1 Pro: which is cheaper, and will that change?
Claude Sonnet 5.5 is cheaper today: $4.00 against $4.50 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Sonnet 5.5 or Gemini 3.1 Pro better for coding?
Claude Sonnet 5.5 scores higher in coding (72 vs 59 on the category index, where 50 is average).
Which is faster, Claude Sonnet 5.5 or Gemini 3.1 Pro?
Claude Sonnet 5.5 streams faster (146 vs 112 output tokens per second, Artificial Analysis 7-day median).
Is Claude Sonnet 5.5 or Gemini 3.1 Pro better for agents and tool use?
Claude Sonnet 5.5 scores higher in agentic tasks (70 vs 57 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Both take about 1M tokens: Claude Sonnet 5.5 1,000,000, Gemini 3.1 Pro 1,048,576.
Which has lower latency?
Gemini 3.1 Pro answers first: 14.5 s against 245.2 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 Sonnet 5.5 vs Gemini 3.1 Pro?
Across the 17 benchmarks both have, Claude Sonnet 5.5 leads 12, Gemini 3.1 Pro leads 5. Independent sources split: Claude Sonnet 5.5 leads on BenchLeader Index; Gemini 3.1 Pro leads on Arena Text.
When was Claude Sonnet 5.5 released?
Claude Sonnet 5.5 was released on 28 Sep 2026.