BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Opus 5.5 vs GPT-6 Sol

Full profiles: Claude Opus 5.5 (Anthropic) and GPT-6 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 12 sources

As of 9 Nov 2026, Claude Opus 5.5 is ahead of GPT-6 Sol on quality (68.9 vs 62.9 on the BenchLeader Index), but GPT-6 Sol is 2.0× cheaper at $4.00 vs $8.00 per 1M tokens blended. Claude Opus 5.5 leads in every category we measure both in.

Key facts (as of 9 Nov 2026)

  • Claude Opus 5.5 scores 68.9 on the BenchLeader Index and GPT-6 Sol scores 62.9 (BenchLeader, 9 Nov 2026).
  • Claude Opus 5.5 costs $8.00 per 1M tokens blended (list price, 9 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 52 benchmarks both models have, Claude Opus 5.5 leads 42 (BenchLeader, 9 Nov 2026).
  • On Arena WebDev, Claude Opus 5.5 is rated 1818 and GPT-6 Sol 1674 (LMArena, as published by 9 Nov 2026).
Claude Opus 5.5 benchmarks max Anthropic GPT-6 Sol benchmarks max OpenAIAdd a third model

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 5.580 vs 67 category score; Arena WebDev 1818 vs 1674High
Agents & tool useClaude Opus 5.563 vs 60 category score; Terminal-Bench 65.8% vs 50.3%Medium
MathsClaude Opus 5.574 vs 69 category score; FrontierMath Tiers 1–3 91.2% vs 89.8%Medium
ReasoningClaude Opus 5.572 vs 66 category score; HLE-Diamond (AA) 67.9% vs 45.2%Medium
KnowledgeClaude Opus 5.574 vs 62 category score; SimpleQA Verified 72.2% vs 60.7%High
Long documentsEither67 vs 67 category score; AA-LCR v1.1 84.7% vs 83.7%Either
Images and other mediaClaude Opus 5.570 vs 61 category score; MMMU-Pro 87.7% vs 83.0%High
Chat quality (human preference)–Only GPT-6 Sol has an Arena rating (64 category score)Not comparable
Lowest costGPT-6 Sol$4.00 vs $8.00 per 1M blended; agentic coding session $0.160 vs $0.320–
Fastest first answerGPT-6 Sol72.1 s (GPT-6 Sol (max)) vs 380.6 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) leads on quality: 68.9 vs 62.9.
  • Claude Opus 5.5 (max) is stronger in agents & tools, coding, knowledge, long context, maths, multimodal, reasoning.
  • GPT-6 Sol (max) is stronger in human preference.
  • GPT-6 Sol (max) is 2.0× cheaper ($4.00 vs $8.00 per 1M blended).

At a glance

SpecClaude Opus 5.5GPT-6 Sol
DeveloperAnthropicOpenAI
Released22 Sep 202622 Sep 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 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / $0.200$2.00 / $10.00 / $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)GPT-6 Sol (max)Leader
Reasoning72.366.2Claude Opus 5.5
Coding80.466.5Claude Opus 5.5
Agents & tools62.759.6Claude Opus 5.5
Maths74.068.5Claude Opus 5.5
Knowledge73.761.5Claude Opus 5.5
Human preference–64.2not comparable
Multimodal70.360.7Claude Opus 5.5
Long context67.166.6level

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 contextMultimodalClaude Opus 5.5, Reasoning: 72.3Claude Opus 5.5, Coding: 80.4Claude Opus 5.5, Agents & tools: 62.7Claude Opus 5.5, Maths: 74.0Claude Opus 5.5, Knowledge: 73.7Claude Opus 5.5, Long context: 67.1Claude Opus 5.5, Multimodal: 70.3GPT-6 Sol, Reasoning: 66.2GPT-6 Sol, Coding: 66.5GPT-6 Sol, Agents & tools: 59.6GPT-6 Sol, Maths: 68.5GPT-6 Sol, Knowledge: 61.5GPT-6 Sol, Long context: 66.6GPT-6 Sol, Multimodal: 60.7

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

ModelIndex

Where sources disagree

Across the 52 benchmarks both have, Claude Opus 5.5 leads 42, GPT-6 Sol leads 9 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 Sol (max)Leader
BenchLeader Index68.962.9Claude Opus 5.5
AA Intelligence Index v5.059.144.2Claude Opus 5.5
Arena Text1506†1457Claude 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 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$0.200
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$0.079
Cost per benchmark task (AA Index)$10.04$2.47
Output tokens per task (AA Index)173k54k
Of which reasoning120k35k
Time per task (AA Index)25 min7 min
Output speed115 tok/s121 tok/s
Time to first answer380.6 s72.1 s
Time to a complete answer771.1 s130.2 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 $2.47 on GPT-6 Sol (max), and Claude Opus 5.5 (max) wrote 3.2× 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 68.9 and takes 381 s to its first answer token; Claude Opus 5.5 (xhigh) scores 65.5 in 84 s, Claude Opus 5.5 (high) scores 65.4 in 28 s. GPT-6 Sol (max) scores 62.9 and takes 72 s to its first answer token; GPT-6 Sol (xhigh) scores 58.6 in 24 s, GPT-6 Sol (high) scores 58.2 in 9 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

134 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 Sol (max)
BenchLeader IndexBenchLeader68.962.9
Agents & tools scoreBenchLeader62.759.6
Coding scoreBenchLeader80.466.5
Knowledge scoreBenchLeader73.761.5
Long context scoreBenchLeader67.166.6
Maths scoreBenchLeader74.068.5
Multimodal scoreBenchLeader70.360.7
Reasoning scoreBenchLeader72.366.2
Human preference scoreBenchLeader–64.2
Blended price $/MBenchLeader$8.00$4.00
Output speedBenchLeader115 tok/s121 tok/s
Time to first answerBenchLeader380.6 s72.1 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.6%94.3%
Arena Hard PromptsArena (LMArena)1530†1483
LiveBench 2.0 ReasoningLiveBench92.2%†–
LiveBench 1.0 ReasoningLiveBench92.2%88.7%
Humanity's Last Exam (AA)Artificial Analysis61.4%47.9%
HLE-Diamond (AA)Artificial Analysis67.9%45.2%
ARC-AGI-1ARC Prize97.5%95.5%
ARC-AGI-2ARC Prize91.7%89.6%
ARC-AGI-3ARC Prize–23.0%
CritPtArtificial Analysis31.7%30.9%
CritPt v2 hard subset (AA)Artificial Analysis68.0%66.5%
MysteryMechanismVals AI49.5%†30.2%
Chess PuzzlesEpoch AI Benchmarking Hub67.0%56.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub71.0%56.0%
LMCAEpoch AI Benchmarking Hub68.2%59.1%
DTBenchEpoch AI Benchmarking Hub98.9%97.3%
Coding
SciCodeSciCode66.9%57.6%
FrontierCodeCognition54.6%†49.3%
Arena CodingArena (LMArena)1546†1520
Arena WebDevArena (LMArena)18181674
LiveBench 2.0 CodingLiveBench87.1%†–
LiveBench 1.0 CodingLiveBench89.3%81.8%
IOIVals AI95.1%†82.6%
Code MigrationVals AI66.7%†57.2%
Code Migration v1.1Vals AI81.0%†–
Show all 134 benchmarks
MetricPublisherClaude Opus 5.5 (max)GPT-6 Sol (max)
Coding
ProgramBenchVals AI18.5%†2.0%
SWE-bench MultimodalVals AI70.2%†–
Vibe Code Bench 1-100Vals AI30.4%†–
Vibe Code Bench v1.1Vals AI90.3%†87.8%
MirrorCodeEpoch AI Benchmarking Hub78.9%†–
CursorBenchCursor57.8%–
ALE-BenchEpoch AI Benchmarking Hub2147.4†2462
FrontierSWEEpoch AI Benchmarking Hub62.3%–
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%43.9%
Startrise FrontendStartrise71.1%†–
GameBench 2 OverallDuelLab GameBench 287.6†72.9†
GameBench 2 by reasoning settingDuelLab GameBench 294.8†79.3†
Design Arena WebsiteDesign Arena1325†1285†
FrontierCode 1.1 (AA)Artificial Analysis52.2%–
FrontierCode 2.0 (AA)Artificial Analysis46.4%35.6%
Agents & tools
Terminal-BenchTerminal-Bench65.8%50.3%
Remote Labor IndexScale AI / CAIS21.3%†–
APEX-AgentsMercor73.5%54.3%
Arena AgentArena (LMArena)207
LiveBench Long AgenticLiveBench72.8%†–
LiveBench BrowserLiveBench88.4%†–
LiveBench Agentic CodingLiveBench71.7%52.9%
Terminal-Bench 2.1 (Vals)Vals AI87.6%†83.2%
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%49.4%
Analyst Agent (AA)Artificial Analysis56.3%–
CUA-benchVals AI14.0%–
CyberBenchVals AI55.4%†78.0%
Finance Agent v2Vals AI58.6%†49.0%
Finance Agent v2.1Vals AI67.8%†–
Harvey's Legal Agent Benchmark v1.1Vals AI9.2%†–
Harvey's Legal Agent Benchmark v1Vals AI3.8%†1.7%
Legal Research BenchVals AI50.5%†28.9%
Robo-benchVals AI14.6%–
SREBenchVals AI33.6%†30.5%
Tax Agent BenchVals AI44.5%†15.0%
Terminal-Bench 4.0 (Vals)Vals AI65.2%†44.4%
Terminal-Bench ScienceVals AI47.1%†30.0%
Time Horizon Index: KSPVals AI91.3%†–
Arena SearchArena (LMArena)1214†1229
Vending-Bench 2Andon Labs9235.3†14427.9†
AutomationBenchArtificial Analysis69.5%61.6%
GDP.pdf (AA)Artificial Analysis26.2%25.2%
Harvey LAB-AA v1.1Harvey4.2%3.6%
AA-Briefcase v1.1Artificial Analysis18001476
GDPxGDPx by SemiAnalysis12.0%–
Design Arena AgenticDesign Arena1334†1212†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis59.0%30.0%
CWE-Bench (AA)Artificial Analysis58.3%64.2%
DeepSec-Bench (AA)Artificial Analysis26.9%46.3%
CyberGym end-to-end (AA)Artificial Analysis0.8%0.0%
FACTS SearchGoogle88.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub91.2%89.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub95.0%90.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%100.0%
ProofBenchVals AI100.0%83.0%†
LiveBench MathematicsLiveBench97.1%96.4%
Arena MathsArena (LMArena)1518†1440
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub72.2%60.7%
LiveBench 2.0 Data AnalysisLiveBench80.3%†–
LiveBench ResearchLiveBench88.9%†–
LiveBench 1.0 Data AnalysisLiveBench80.3%81.2%
AA-Omniscience v1.1Artificial Analysis48.121.4
PRBench LegalScale AI SEAL47.6%†38.6%†
BioMysteryBenchVals AI79.3%†74.8%
ClaimBenchVals AI100.0%†–
Excel Modeling BenchmarkVals AI75.9%†71.5%
Excel Modeling Benchmark v1.1Vals AI75.8%†–
MedCodeVals AI49.8%†47.1%
MedScribeVals AI91.4%†82.0%
Public Benefits Bench v1.1Vals AI70.6%†56.6%
EBR-benchEpoch AI Benchmarking Hub71.4%53.3%
GDP.pdfEpoch AI Benchmarking Hub30.6%26.4%
AA-Omniscience v1.1: accuracyArtificial Analysis65.5%51.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis49.7%39.1%
HealthBench Professional (AA)OpenAI59.9%62.3%
Instruction following
LiveBench LanguageLiveBench86.3%85.3%
LiveBench Instruction FollowingLiveBench65.7%68.6%
Arena Instruction FollowingArena (LMArena)1519†1448
Human preference
Arena TextArena (LMArena)1506†1457
EQ-Bench 4EQ-Bench1340†–
Arena Creative WritingArena (LMArena)1517†1430
Arena Multi-turnArena (LMArena)1500†1466
Arena Longer QueriesArena (LMArena)1520†1466
Multimodal
Arena VisionArena (LMArena)1324†1232
LiveBench DesignLiveBench83.3%†–
MMMU-ProArtificial Analysis87.7%83.0%
SAGEVals AI91.3%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub51.2%†36.9%†
Code2Video-AAArtificial Analysis1536–
AA-3DArtificial Analysis12021131
Long context
AA-LCR v1.1Artificial Analysis84.7%83.7%
MLCRArtificial Analysis27.8%33.9%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.4†164.1†
LiveBench 2.0LiveBench83.4%†–
LiveBench 1.0LiveBench83.2%79.3%
AA Intelligence Index v5.0Artificial Analysis59.144.2
AA Intelligence Index v4.3.2Artificial Analysis57.647.6
AA Progress Index v1Artificial Analysis350334
Vals IndexVals AI70.1†–
Vals Finance IndexVals AI65.3%†–
Vals RSI IndexVals AI37.3%28.1%
Vals Science IndexVals AI58.6%†45.0%
Vals Router IndexVals AI64.2%†–
AA Cyber IndexArtificial Analysis28.736.8
Safety & honesty
FORTRESSScale AI SEAL5.8%13.5%†

Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), 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 Sol (max): BenchLeader Index 63.5 → 62.9.
  • Claude Opus 5.5 (max): 2 score revisions.
  • GPT-6 Sol (max): 2 score revisions.
  • Claude Opus 5.5 (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.
  • Claude Opus 5.5 (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • GPT-6 Sol (max): 6 new results (AA Intelligence Index v5.0, AA-Omniscience v1.1, CritPt v2 hard subset (AA)…).
  • 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 GPT-6 Sol: questions

Is Claude Opus 5.5 better than GPT-6 Sol?
Claude Opus 5.5 (max) leads on quality: 68.9 vs 62.9. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5.5 (max) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
Claude Opus 5.5 vs GPT-6 Sol: which is cheaper, and will that change?
GPT-6 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 Sol better for coding?
Claude Opus 5.5 scores higher in coding (80 vs 67 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 1674 for GPT-6 Sol.
Which is faster, Claude Opus 5.5 or GPT-6 Sol?
GPT-6 Sol streams faster (121 vs 115 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 5.5 or GPT-6 Sol better for agents and tool use?
Claude Opus 5.5 scores higher in agentic tasks (63 vs 60 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 50.3% for GPT-6 Sol.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (67 vs 67). Both take about 1.1M tokens: Claude Opus 5.5 1,000,000, GPT-6 Sol 1,050,000.
Which has lower latency?
GPT-6 Sol answers first: 72.1 s against 380.6 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 Sol?
Across the 52 benchmarks both have, Claude Opus 5.5 leads 42, GPT-6 Sol leads 9 and 1 is a tie. 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.