BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Opus 5 vs GPT-6 Sol

Full profiles: Claude Opus 5 (Anthropic) and GPT-6 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 15 sources

As of 9 Nov 2026, Claude Opus 5 and GPT-6 Sol are neck and neck on quality (65.2 vs 62.9 on the BenchLeader Index, inside the ±4.4 margin), and GPT-6 Sol is 2.5× cheaper at $4.00 vs $10.00 per 1M tokens blended. Choose Claude Opus 5 for human preference (76 vs 64), agents & tools (65 vs 60), and reasoning (71 vs 66) and fast first answers (2.9 s vs 72.1 s); choose GPT-6 Sol for maths (69 vs 66), where it also streams ~2× faster.

Key facts (as of 9 Nov 2026)

  • Claude Opus 5 scores 65.2 on the BenchLeader Index and GPT-6 Sol scores 62.9 (BenchLeader, 9 Nov 2026).
  • Claude Opus 5 costs $10.00 per 1M tokens blended (list price, 9 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 9 Nov 2026).
  • GPT-6 Sol streams ~2× faster than Claude Opus 5 (Artificial Analysis, 7-day median, 9 Nov 2026).
  • Of the 23 benchmarks both models have, Claude Opus 5 leads 17 (BenchLeader, 9 Nov 2026).
Claude Opus 5 benchmarks 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 568 vs 67 category score; IOI 84.3% vs 82.6%Medium
Agents & tool useClaude Opus 565 vs 60 category score; Terminal-Bench 2.1 (Vals) 84.6% vs 83.2%Medium
MathsGPT-6 Sol69 vs 66 category score; OTIS Mock AIME 100.0% vs 97.8%Medium
ReasoningClaude Opus 571 vs 66 category score; GPQA Diamond 92.9% vs 94.3%Medium
KnowledgeClaude Opus 566 vs 62 category score; BioMysteryBench 79.3% vs 74.8%Medium
Chat quality (human preference)Claude Opus 576 vs 64 on Arena votesHigh
Lowest costGPT-6 Sol$4.00 vs $10.00 per 1M blended; agentic coding session $0.160 vs $0.400–
Fastest first answerClaude Opus 52.9 s (Claude Opus 5) vs 72.1 s (GPT-6 Sol (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 and GPT-6 Sol (max) are neck and neck on quality (65.2 vs 62.9, within the ±4.4 margin).
  • Claude Opus 5 is stronger in agents & tools, coding, human preference, knowledge, reasoning.
  • GPT-6 Sol (max) is stronger in maths, long context, multimodal.
  • GPT-6 Sol (max) is 2.5× cheaper ($4.00 vs $10.00 per 1M blended).
  • GPT-6 Sol (max) streams 1.9× faster (121 vs 64 tokens per second).

At a glance

SpecClaude Opus 5GPT-6 Sol
DeveloperAnthropicOpenAI
Released24 Jul 202622 Sep 2026
Context window (tokens)1,000,0001,050,000
Compared atClaude Opus 5GPT-6 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$2.00 / $10.00 / $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 Opus 5GPT-6 Sol (max)Leader
Reasoning71.266.2Claude Opus 5
Coding67.966.5Claude Opus 5
Agents & tools65.159.6Claude Opus 5
Maths65.868.5GPT-6 Sol
Knowledge66.361.5Claude Opus 5
Human preference75.964.2Claude Opus 5
Multimodal–60.7not comparable
Long context–66.6not 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 & toolsMathsKnowledgeHumanpreferenceClaude Opus 5, Reasoning: 71.2Claude Opus 5, Coding: 67.9Claude Opus 5, Agents & tools: 65.1Claude Opus 5, Maths: 65.8Claude Opus 5, Knowledge: 66.3Claude Opus 5, Human preference: 75.9GPT-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, Human preference: 64.2

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

ModelIndex

Where sources disagree

Across the 23 benchmarks both have, Claude Opus 5 leads 17, GPT-6 Sol leads 6. Every overall index that rates both puts Claude Opus 5 ahead.

Overall indexClaude Opus 5GPT-6 Sol (max)Leader
BenchLeader Index65.262.9neck and neck
AA Intelligence Index v5.044.2†44.2level
Arena Text1490†1457Claude 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureClaude Opus 5GPT-6 Sol (max)
Blended price per 1M tokens$10.00$4.00
Input / output per 1M$5.00 / $25.00$2.00 / $10.00
Cached input per 1M$0.500$0.200
Price per task: chat reply$0.0095$0.0038
Price per task: summarize a 30-page report$0.075$0.030
Price per task: code edit$0.068$0.027
Price per task: agentic coding session$0.400$0.160
Price per task: structured extraction$0.015$0.0060
Agentic coding session, input mostly cached$0.198$0.079
Cost per benchmark task (AA Index)–$2.47
Output tokens per task (AA Index)–54k
Of which reasoning–35k
Time per task (AA Index)–7 min
Output speed64 tok/s121 tok/s
Time to first answer2.9 s72.1 s
Time to a complete answer–130.2 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5 scores 65.2 and takes 3 s to its first answer token; Claude Opus 5 (max) scores 65.1 in 60 s, Claude Opus 5 (high) scores 64.2 in 14 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

136 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 5GPT-6 Sol (max)
BenchLeader IndexBenchLeader65.262.9
Agents & tools scoreBenchLeader65.159.6
Coding scoreBenchLeader67.966.5
Human preference scoreBenchLeader75.964.2
Knowledge scoreBenchLeader66.361.5
Maths scoreBenchLeader65.868.5
Reasoning scoreBenchLeader71.266.2
Long context scoreBenchLeader–66.6
Multimodal scoreBenchLeader–60.7
Blended price $/MBenchLeader$10.00$4.00
Output speedBenchLeader64 tok/s121 tok/s
Time to first answerBenchLeader2.9 s72.1 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub92.9%94.3%
SimpleBenchSimpleBench80.6%–
Arena Hard PromptsArena (LMArena)1513†1483
LiveBench 1.0 ReasoningLiveBench91.2%†88.7%
GPQA Diamond (AA)Artificial Analysis93.2%†–
Humanity's Last Exam (AA)Artificial Analysis54.9%†47.9%
HLE-Diamond (AA)Artificial Analysis44.8%†45.2%
GPQA Diamond (Vals)Vals AI93.4%–
ARC-AGI-1ARC Prize97.5%†95.5%
ARC-AGI-2ARC Prize90.4%†89.6%
ARC-AGI-3ARC Prize30.2%†23.0%
CritPtArtificial Analysis29.1%†30.9%
CritPt v2 hard subset (AA)Artificial Analysis50.0%†66.5%
MysteryMechanismVals AI37.4%30.2%
Chess PuzzlesEpoch AI Benchmarking Hub43.0%†56.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub37.0%56.0%
LMCAEpoch AI Benchmarking Hub63.3%†59.1%
DTBenchEpoch AI Benchmarking Hub97.6%†97.3%
ForecastBenchForecastBench66.5%†–
BTF-3Epoch AI Benchmarking Hub12.0%†–
Coding
SciCodeSciCode56.4%†57.6%
WeirdMLWeirdML86.3%–
FrontierCodeCognition53.4%†49.3%
Arena CodingArena (LMArena)1528†1520
Arena WebDevArena (LMArena)1691†1674
Show all 136 benchmarks
MetricPublisherClaude Opus 5GPT-6 Sol (max)
Coding
LiveBench 1.0 CodingLiveBench81.5%†81.8%
LiveCodeBenchVals AI89.0%–
IOIVals AI84.3%82.6%
SWE-bench (Vals)Vals AI97.0%–
Code MigrationVals AI57.5%57.2%
ProgramBenchVals AI3.0%2.0%
Vibe Code Bench 1-100Vals AI28.5%–
Vibe Code Bench v1.1Vals AI88.4%87.8%
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†2462
FrontierSWEEpoch AI Benchmarking Hub52.0%†–
Terminal-Bench 4.0 (AA)Artificial Analysis49.0%†43.9%
Terminal-Bench 2.1 (AA)Artificial Analysis89.1%†–
Startrise FrontendStartrise82.3%–
GameBench 2 OverallDuelLab GameBench 276.672.9†
GameBench 2 by reasoning settingDuelLab GameBench 284.7†79.3†
Design Arena WebsiteDesign Arena13061285†
FrontierCode 2.0 (AA)Artificial Analysis31.1%†35.6%
Agents & tools
Terminal-BenchTerminal-Bench52.1%†50.3%
OSWorld-Verified 2.0OSWorld31.4%†–
APEX-AgentsMercor65.8%†54.3%
Arena AgentArena (LMArena)7.5†7
LiveBench Agentic CodingLiveBench65.2%†52.9%
Terminal-Bench 2.1 (Vals)Vals AI84.6%83.2%
MCP AtlasScale AI SEAL85.8%†–
HiL-BenchScale AI SEAL57.0%–
τ³-bench Bankingτ²-bench48.7%†–
τ³-Banking (AA)Artificial Analysis42.1%†–
ITBench SRE (AA)Artificial Analysis–49.4%
Analyst Agent (AA)Artificial Analysis53.8%†–
CUA-benchVals AI9.0%†–
CyberBenchVals AI65.4%78.0%
Finance Agent v2Vals AI58.6%49.0%
Harvey's Legal Agent Benchmark v1Vals AI6.7%1.7%
Legal Research BenchVals AI55.3%28.9%
SkillsBenchVals AI60.4%–
SREBenchVals AI12.2%30.5%
Tax Agent BenchVals AI47.1%15.0%
Terminal-Bench 4.0 (Vals)Vals AI53.5%44.4%
Terminal-Bench ScienceVals AI27.1%30.0%
Time Horizon Index: KSPVals AI18.8%–
Arena SearchArena (LMArena)1214†1229
BALROGBALROG63.4%†–
PostTrainBenchEpoch AI Benchmarking Hub35.0%–
GBAEvalEpoch AI Benchmarking Hub79.6%–
Vending-Bench 2Andon Labs11181.914427.9†
AutomationBenchArtificial Analysis56.6%†61.6%
GDP.pdf (AA)Artificial Analysis21.6%†25.2%
Harvey LAB-AA v1.1Harvey–3.6%
EnterpriseOps-GymArtificial Analysis47.5%†–
AA-Briefcase v1.1Artificial Analysis1655†1476
Design Arena AgenticDesign Arena12661212†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis28.6%†30.0%
CWE-Bench (AA)Artificial Analysis–64.2%
DeepSec-Bench (AA)Artificial Analysis25.9%†46.3%
CyberGym end-to-end (AA)Artificial Analysis–0.0%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub85.6%†89.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub73.2%†90.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub97.8%100.0%
ProofBenchVals AI99.0%†83.0%†
LiveBench MathematicsLiveBench95.7%†96.4%
Arena MathsArena (LMArena)1515†1440
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub59.9%†60.7%
LiveBench 1.0 Data AnalysisLiveBench74.5%†81.2%
AA-Omniscience v1.1Artificial Analysis37.6†21.4
MMLU-ProVals AI91.6%–
LegalBenchVals AI87.0%–
CorpFinVals AI73.2%–
TaxEvalVals AI75.1%–
PRBench LegalScale AI SEAL–38.6%†
BioMysteryBenchVals AI79.3%74.8%
Excel Modeling BenchmarkVals AI73.6%71.5%
MedCodeVals AI63.6%47.1%
MedScribeVals AI91.0%82.0%
Public Benefits Bench v1.1Vals AI76.9%56.6%
DrugDiscoveryBenchScale AI SEAL53.7%†–
EBR-benchEpoch AI Benchmarking Hub45.7%†53.3%
GDP.pdfEpoch AI Benchmarking Hub24.0%†26.4%
AA-Omniscience v1.1: accuracyArtificial Analysis60.9%†51.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.6%†39.1%
HealthBench Professional (AA)OpenAI–62.3%
Instruction following
LiveBench LanguageLiveBench88.7%†85.3%
LiveBench Instruction FollowingLiveBench63.8%†68.6%
Arena Instruction FollowingArena (LMArena)1494†1448
Human preference
Arena TextArena (LMArena)1489†1457
EQ-Bench 4EQ-Bench1365–
Arena Creative WritingArena (LMArena)1473†1430
Arena Multi-turnArena (LMArena)1486†1466
Arena Longer QueriesArena (LMArena)1501†1466
Multimodal
Arena VisionArena (LMArena)1317†1232
MMMU-ProArtificial Analysis84.7%†83.0%
MMMU-Pro (Vals)Vals AI89.9%–
MortgageTaxVals AI72.1%–
Blueprint-Bench 2Epoch AI Benchmarking Hub30.4%36.9%†
AA-3DArtificial Analysis–1131
Long context
AA-LCR v1.1Artificial Analysis79.3%†83.7%
Arena DocumentArena (LMArena)1486†–
MLCRArtificial Analysis11.1%†33.9%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub164.4164.1†
LiveBench 1.0LiveBench80.1%†79.3%
AA Intelligence Index v5.0Artificial Analysis44.2†44.2
AA Intelligence Index v4.3.2Artificial Analysis50.8†47.6
AA Progress Index v1Artificial Analysis333.7†334
Vals RSI IndexVals AI33.0%†28.1%
Vals Science IndexVals AI47.9%45.0%
Vals Multimodal IndexVals AI73.9%–
AA Cyber IndexArtificial Analysis–36.8
Safety & honesty
FORTRESSScale AI SEAL16.8%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: 1 score revision.
  • GPT-6 Sol (max): 2 score revisions.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.
  • Claude Opus 5: 1 score revision.
  • GPT-6 Sol (max): 6 new results (AA Intelligence Index v5.0, AA-Omniscience v1.1, CritPt v2 hard subset (AA)…).
  • GPT-6 Sol (max): 1 score revision.
  • Claude Opus 5: 1 score revision.
  • Claude Opus 5: 1 score revision.

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

Claude Opus 5 vs GPT-6 Sol: questions

Is Claude Opus 5 better than GPT-6 Sol?
Claude Opus 5 and GPT-6 Sol (max) are neck and neck on quality (65.2 vs 62.9, within the ±4.4 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
Claude Opus 5 vs GPT-6 Sol: which is cheaper, and will that change?
GPT-6 Sol is cheaper today: $4.00 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 5 or GPT-6 Sol better for coding?
Claude Opus 5 scores higher in coding (68 vs 67 on the category index, where 50 is average). On IOI, the top shared coding benchmark, it is 84.3% for Claude Opus 5 against 82.6% for GPT-6 Sol.
Which is faster, Claude Opus 5 or GPT-6 Sol?
GPT-6 Sol streams ~2× faster (121 vs 64 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 5 or GPT-6 Sol better for agents and tool use?
Claude Opus 5 scores higher in agentic tasks (65 vs 60 on the category index, where 50 is average). On Terminal-Bench 2.1 (Vals), the top shared agents & tools benchmark, it is 84.6% for Claude Opus 5 against 83.2% for GPT-6 Sol.
More questions (4)
Which is better for long documents?
Both take about 1.1M tokens: Claude Opus 5 1,000,000, GPT-6 Sol 1,050,000.
Which has lower latency?
Claude Opus 5 answers first: 2.9 s against 72.1 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 vs GPT-6 Sol?
Across the 23 benchmarks both have, Claude Opus 5 leads 17, GPT-6 Sol leads 6. Every overall index that rates both puts Claude Opus 5 ahead.
When was GPT-6 Sol released?
GPT-6 Sol was released on 22 Sep 2026.