BenchLeader

Claude Opus 5.5 vs GPT-6.2 Sol

Full profiles: Claude Opus 5.5 (Anthropic) and GPT-6.2 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 12 sources

As of 19 Nov 2026, Claude Opus 5.5 and GPT-6.2 Sol are neck and neck on quality (67.8 vs 64.6 on the BenchLeader Index, inside the ±4.3 margin), and GPT-6.2 Sol is 2.0× cheaper at $4.00 vs $8.00 per 1M tokens blended. Choose Claude Opus 5.5 for knowledge (71 vs 65) and coding (77 vs 75), where it also streams faster; choose GPT-6.2 Sol for fast first answers (78.8 s vs 352.2 s) and agents & tools (65 vs 64).

Key facts (as of 19 Nov 2026)

  • Claude Opus 5.5 scores 67.8 on the BenchLeader Index and GPT-6.2 Sol scores 64.6 (BenchLeader, 19 Nov 2026).
  • Claude Opus 5.5 costs $8.00 per 1M tokens blended (list price, 19 Nov 2026).
  • GPT-6.2 Sol costs $4.00 per 1M tokens blended (list price, 19 Nov 2026).
  • Claude Opus 5.5 streams faster than GPT-6.2 Sol (Artificial Analysis, 7-day median, 19 Nov 2026).
  • Of the 48 benchmarks both models have, Claude Opus 5.5 leads 31 (BenchLeader, 19 Nov 2026).
  • On Arena WebDev, Claude Opus 5.5 is rated 1818 and GPT-6.2 Sol 1757 (LMArena, as published by 19 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 5.577 vs 75 category score; Arena WebDev 1818 vs 1757Medium
Agents & tool useGPT-6.2 Sol65 vs 64 category score; CWE-Bench (AA) 61.7% vs 58.3%Medium
ReasoningEither71 vs 70 category score; HLE-Diamond (AA) 67.9% vs 64.0%Either
KnowledgeClaude Opus 5.571 vs 65 category score; AA-Omniscience v1.1 48.1 vs 40.4Medium
Lowest costGPT-6.2 Sol$4.00 vs $8.00 per 1M blended; agentic coding session $0.160 vs $0.320–
Fastest first answerGPT-6.2 Sol78.8 s (GPT-6.2 Sol (max)) vs 352.2 s (Claude Opus 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 Opus 5.5 (max) and GPT-6.2 Sol (max) are neck and neck on quality (67.8 vs 64.6, within the ±4.3 margin).
  • Claude Opus 5.5 (max) is stronger in coding, composite, knowledge, reasoning.
  • GPT-6.2 Sol (max) is stronger in agents & tools.
  • GPT-6.2 Sol (max) is 2.0× cheaper ($4.00 vs $8.00 per 1M blended).
  • Claude Opus 5.5 (max) streams 1.6× faster (115 vs 74 tokens per second).

At a glance

SpecClaude Opus 5.5GPT-6.2 Sol
DeveloperAnthropicOpenAI
Released22 Sep 202617 Nov 2026
Context window (tokens)1,000,0001,050,000
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)GPT-6.2 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / $0.200$2.00 / $10.00 / $0.100
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)GPT-6.2 Sol (max)Leader
Reasoning70.770.1level
Coding77.474.5Claude Opus 5.5
Agents & tools64.065.1GPT-6.2 Sol
Maths72.7–not comparable
Knowledge71.265.4Claude Opus 5.5
Multimodal69.9–not comparable
Long context67.1–not comparable
Composite68.064.5Claude Opus 5.5

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 & toolsKnowledgeClaude Opus 5.5, Reasoning: 70.7Claude Opus 5.5, Coding: 77.4Claude Opus 5.5, Agents & tools: 64.0Claude Opus 5.5, Knowledge: 71.2GPT-6.2 Sol, Reasoning: 70.1GPT-6.2 Sol, Coding: 74.5GPT-6.2 Sol, Agents & tools: 65.1GPT-6.2 Sol, Knowledge: 65.4

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

Model, click to add or removeIndex

Where sources disagree

Across the 48 benchmarks both have, Claude Opus 5.5 leads 31, GPT-6.2 Sol leads 16 and 1 is a tie. Every overall index that rates both puts Claude Opus 5.5 ahead.

Overall indexClaude Opus 5.5 (max)GPT-6.2 Sol (max)Leader
BenchLeader Index67.864.6neck and neck
AA Intelligence Index v5.0.159.157.3Claude Opus 5.5
Vals Index70.166.1Claude 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)GPT-6.2 Sol (max)
Blended price per 1M tokens$8.00$4.00
Input / output per 1M$4.00 / $20.00$2.00 / $10.00
Cached input per 1M$0.200$0.100
Price per task: chat reply$0.0076$0.0038
Price per task: summarize a 30-page report$0.060$0.030
Price per task: code edit$0.054$0.027
Price per task: agentic coding session$0.320$0.160
Price per task: structured extraction$0.012$0.0060
Agentic coding session, input mostly cached$0.149$0.074
Cost per benchmark task (AA Index)$10.04$1.01
Output tokens per task (AA Index)173k40k
Of which reasoning120k23k
Time per task (AA Index)25 min9 min
Output speed115 tok/s74 tok/s
Time to first answer352.2 s78.8 s
Time to a complete answer, last measured 13 Nov 2026711.4 s–

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $10.04 on Claude Opus 5.5 (max) and $1.01 on GPT-6.2 Sol (max), and Claude Opus 5.5 (max) wrote 4.3× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5.5 (max) scores 67.8 and takes 352 s to its first answer token; Claude Opus 5.5 (high) scores 65.5 in 22 s, Claude Opus 5.5 (xhigh) scores 64.6 in 64 s. GPT-6.2 Sol (max) scores 64.6 and takes 79 s to its first answer token; GPT-6.2 Sol (xhigh) scores 63.3 in 32 s, GPT-6.2 Sol (high) scores 62.3 in 12 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

170 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)GPT-6.2 Sol (max)
BenchLeader IndexBenchLeader67.864.6
Agents & tools scoreBenchLeader64.065.1
Coding scoreBenchLeader77.474.5
Composite scoreBenchLeader68.064.5
Knowledge scoreBenchLeader71.265.4
Long context scoreBenchLeader67.1–
Maths scoreBenchLeader72.7–
Multimodal scoreBenchLeader69.9–
Reasoning scoreBenchLeader70.770.1
Blended price $/MBenchLeader$8.00$4.00
Output speedBenchLeader115 tok/s74 tok/s
Time to first answerBenchLeader352.2 s78.8 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.6%–
SimpleBenchSimpleBench88.4%†–
Arena Hard PromptsArena (LMArena)1531†–
LiveBench 2.0 ReasoningLiveBench92.2%90.6%
LiveBench 1.0 ReasoningLiveBench92.2%–
Humanity's Last Exam (AA)Artificial Analysis61.4%–
HLE-Diamond (AA)Artificial Analysis67.9%64.0%
Kagi LLM BenchmarkKagi LLM Benchmark–67.0%†
ARC-AGI-1ARC Prize97.5%97.5%
ARC-AGI-2ARC Prize91.7%85.8%
ARC-AGI-3ARC Prize–98.2%
CritPtArtificial Analysis31.7%–
CritPt v2 hard subset (AA)Artificial Analysis68.0%62.5%
MysteryMechanismVals AI49.5%36.9%
HLE-Diamond (Scale)Scale AI SEAL55.0%†56.5%†
Arena ExpertArena (LMArena)1550†–
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%†–
Coding
SciCodeSciCode66.9%–
FrontierCodeCognition54.6%†–
Arena CodingArena (LMArena)1547†–
Arena WebDevArena (LMArena)18181757
Show all 170 benchmarks
MetricPublisherClaude Opus 5.5 (max)GPT-6.2 Sol (max)
Coding
LiveBench 2.0 CodingLiveBench87.1%83.7%
LiveBench 1.0 CodingLiveBench89.3%–
IOIVals AI95.1%–
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%87.6%
Vibe Code Bench 1-100 v1.1Vals AI30.9%40.9%
SWE Atlas v1.1Scale AI SEAL77.5%†60.5%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL77.4%†61.3%†
SWE Atlas v1.1: Test WritingScale AI SEAL77.8%†64.4%†
SWE Atlas v1.1: RefactoringScale AI SEAL77.1%†55.7%†
MirrorCodeEpoch AI Benchmarking Hub95.6%–
CursorBenchCursor57.8%–
ALE-BenchEpoch AI Benchmarking Hub2147.4†–
FrontierSWEEpoch AI Benchmarking Hub62.3%–
WeirdML v3WeirdML31.2%†–
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%60.1%
Startrise FrontendStartrise80.2%†–
GameBench 2 OverallDuelLab GameBench 287.6†–
GameBench 2 by reasoning settingDuelLab GameBench 294.7†–
Design Arena WebsiteDesign Arena1321†–
FrontierCode 1.1 (AA)Artificial Analysis52.2%–
FrontierCode 2.0 (AA)Artificial Analysis46.4%44.4%
Agents & tools
Terminal-BenchTerminal-Bench65.8%61.5%
Remote Labor IndexScale AI / CAIS21.3%†–
APEX-AgentsMercor73.5%–
Arena AgentArena (LMArena)18.611.3
LiveBench Long AgenticLiveBench72.8%63.6%
LiveBench BrowserLiveBench88.4%88.2%
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%53.8%
CUA-benchVals AI14.0%–
CyberBenchVals AI55.4%–
Finance Agent v2Vals AI58.6%–
Finance Agent v2.1Vals AI67.8%58.9%
Harvey's Legal Agent Benchmark v1.1Vals AI9.2%12.1%
Harvey's Legal Agent Benchmark v1Vals AI3.8%–
Legal Research BenchVals AI50.5%37.0%
Robo-benchVals AI14.6%–
SREBenchVals AI33.6%–
Tax Agent BenchVals AI44.5%24.8%
Terminal-Bench 4.0 (Vals)Vals AI65.2%60.6%
Terminal-Bench ScienceVals AI47.1%58.6%
Time Horizon Index: KSPVals AI91.3%–
Web Search IndexVals AI53.8%–
Arena SearchArena (LMArena)1213†–
Arena Agent Task CompletionArena (LMArena)19.210.9
PostTrainBenchEpoch AI Benchmarking Hub43.8%–
GBAEvalEpoch AI Benchmarking Hub90.6%†–
Vending-Bench 2Andon Labs9235.3†–
SpireClimbEpoch AI Benchmarking Hub5.8%–
AutomationBenchArtificial Analysis69.5%71.3%
GDP.pdf (AA)Artificial Analysis26.2%30.0%
Harvey LAB-AA v1.1Harvey4.2%11.1%
EnterpriseOps-GymArtificial Analysis–28.9%
AA-Briefcase v1.1Artificial Analysis18001612
GDPxGDPx by SemiAnalysis11.9%–
Design Arena AgenticDesign Arena1325†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis59.0%67.6%
CWE-Bench (AA)Artificial Analysis58.3%61.7%
DeepSec-Bench (AA)Artificial Analysis26.9%51.6%
CyberGym end-to-end (AA)Artificial Analysis0.8%0.0%
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%–
ProofBenchVals AI100.0%–
LiveBench MathematicsLiveBench97.1%–
ArXivMathMathArena82.6%†–
BrokenArXivMathArena77.3%†–
Autoform-HardVals AI–85.7%
Arena MathsArena (LMArena)1516†–
FrontierMath ErdősEpoch AI Benchmarking Hub2.9%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub72.2%–
LiveBench 2.0 Data AnalysisLiveBench80.3%81.1%
LiveBench ResearchLiveBench88.9%90.1%
LiveBench 1.0 Data AnalysisLiveBench80.3%–
AA-Omniscience v1.1Artificial Analysis48.140.4
PRBench LegalScale AI SEAL47.6%†43.3%†
BioMysteryBenchVals AI79.3%77.8%
ClaimBenchVals AI100.0%–
Excel Modeling BenchmarkVals AI75.9%–
Excel Modeling Benchmark v1.1Vals AI75.8%74.3%
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%–
DrugDiscoveryBenchScale AI SEAL–62.2%†
EBR-benchEpoch AI Benchmarking Hub71.4%–
GDP.pdfEpoch AI Benchmarking Hub48.8%–
AA-Omniscience v1.1: accuracyArtificial Analysis65.5%61.6%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis49.7%44.6%
HealthBench Professional (AA)OpenAI59.9%–
FACTS ParametricGoogle58.7%†–
Instruction following
LiveBench LanguageLiveBench86.3%–
LiveBench Instruction FollowingLiveBench65.7%–
MultiChallengeScale AI SEAL–72.0%†
Arena Instruction FollowingArena (LMArena)1517†–
Human preference
Arena TextArena (LMArena)1507†–
EQ-Bench 4EQ-Bench1340†–
EQ-Bench Creative Writing v3EQ-Bench2051†–
Arena Creative WritingArena (LMArena)1516†–
Arena Multi-turnArena (LMArena)1501†–
Arena Longer QueriesArena (LMArena)1522†–
Multimodal
Arena VisionArena (LMArena)1324†–
LiveBench DesignLiveBench83.3%80.0%
MMMU-ProArtificial Analysis87.7%–
SAGEVals AI91.3%–
Humanity's Sixth SenseScale AI SEAL44.6%†56.8%†
Blueprint-Bench 2Epoch AI Benchmarking Hub51.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub83.3%–
VIALS-AAHandshake AI61.5%62.7%
Code2Video-AAArtificial Analysis1536–
AA-3DArtificial Analysis12021259
FACTS MultimodalGoogle56.4%†–
Long context
AA-LCR v1.1Artificial Analysis84.7%–
MLCRArtificial Analysis27.8%37.2%
FACTS GroundingGoogle62.5%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.7†–
LiveBench 2.0LiveBench83.4%80.3%
LiveBench 1.0LiveBench83.2%–
AA Intelligence Index v5.0.1Artificial Analysis59.157.3
AA Intelligence Index v4.3.2Artificial Analysis57.6–
AA Progress Index v1Artificial Analysis350–
Vals IndexVals AI70.166.1
Vals Finance IndexVals AI65.3%56.7%
Vals RSI IndexVals AI37.3%–
Vals Science IndexVals AI58.6%57.8%
Vals Router IndexVals AI64.2%†–
Vals Legal IndexVals AI72.4%66.7%
AA Cyber IndexArtificial Analysis28.737.8
Safety & honesty
FORTRESSScale AI SEAL5.8%–
DistressBenchScale AI SEAL75.6%†–

Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-6.2 Sol (max): BenchLeader Index 63.2 → 64.6.
  • GPT-6.2 Sol (max): 4 new results (VIALS-AA, Arena WebDev, Arena Agent…).
  • GPT-6.2 Sol (max): BenchLeader Index 62.4 → 63.2.
  • GPT-6.2 Sol (max): 2 new results (Vibe Code Bench 1-100 v1.1, Terminal-Bench).
  • 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.

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

Claude Opus 5.5 vs GPT-6.2 Sol: questions

Is Claude Opus 5.5 better than GPT-6.2 Sol?
Claude Opus 5.5 (max) and GPT-6.2 Sol (max) are neck and neck on quality (67.8 vs 64.6, within the ±4.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 19 Nov 2026, so check the category scores for your use.
Claude Opus 5.5 vs GPT-6.2 Sol: which is cheaper, and will that change?
GPT-6.2 Sol is cheaper today: $4.00 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 5.5 or GPT-6.2 Sol better for coding?
Claude Opus 5.5 scores higher in coding (77 vs 75 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1818 for Claude Opus 5.5 against 1757 for GPT-6.2 Sol.
Which is faster, Claude Opus 5.5 or GPT-6.2 Sol?
Claude Opus 5.5 streams faster (115 vs 74 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 5.5 or GPT-6.2 Sol better for agents and tool use?
GPT-6.2 Sol scores higher in agentic tasks (65 vs 64 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 65.8% for Claude Opus 5.5 against 61.5% for GPT-6.2 Sol.
More questions (4)
Which is better for long documents?
Both take about 1.1M tokens: Claude Opus 5.5 1,000,000, GPT-6.2 Sol 1,050,000.
Which has lower latency?
GPT-6.2 Sol answers first: 78.8 s against 352.2 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 Opus 5.5 vs GPT-6.2 Sol?
Across the 48 benchmarks both have, Claude Opus 5.5 leads 31, GPT-6.2 Sol leads 16 and 1 is a tie. Every overall index that rates both puts Claude Opus 5.5 ahead.
When was GPT-6.2 Sol released?
GPT-6.2 Sol was released on 17 Nov 2026.