BenchLeader

Claude Sonnet 5 vs GPT-5.6 Terra

Full profiles: Claude Sonnet 5 (Anthropic) and GPT-5.6 Terra (OpenAI): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, Claude Sonnet 5 and GPT-5.6 Terra are neck and neck on quality (59.0 vs 60.1 on the BenchLeader Index, inside the ±4.7 margin), and they cost about the same at $4.00 vs $4.50 per 1M tokens blended. Choose Claude Sonnet 5 for reasoning (65 vs 55); choose GPT-5.6 Terra for agents & tools (63 vs 53) and long context (64 vs 63).

Key facts (as of 16 Nov 2026)

  • Claude Sonnet 5 scores 59.0 on the BenchLeader Index and GPT-5.6 Terra scores 60.1 (BenchLeader, 16 Nov 2026).
  • Claude Sonnet 5 costs $4.00 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-5.6 Terra costs $4.50 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 28 benchmarks both models have, GPT-5.6 Terra leads 18 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Claude Sonnet 5 is rated 1539 and GPT-5.6 Terra 1520 (LMArena, as published by 16 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
CodingEither60 vs 59 category score; Arena WebDev 1539 vs 1520Either
Agents & tool useGPT-5.6 Terra63 vs 53 category score; Arena Agent -1.8 vs 2High
MathsEither65 vs 66 category score; Arena Maths 1472 vs 1478Either
ReasoningClaude Sonnet 565 vs 55 category score; Arena Hard Prompts 1490 vs 1491High
Long documentsGPT-5.6 Terra64 vs 63 category score; AA-LCR v1.1 79.0% vs 76.7%Medium
Images and other mediaEither61 vs 61 category score; Arena Vision 1272 vs 1269Either
Chat quality (human preference)Either65 vs 66 on Arena votesEither
Lowest costEither$4.00 vs $4.50 per 1M blended; agentic coding session $0.160 vs $0.168–
Fastest first answerEither15.8 s (Claude Sonnet 5 (high)) vs 19.2 s (GPT-5.6 Terra (xhigh)) 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 (high) and GPT-5.6 Terra (xhigh) are neck and neck on quality (59.0 vs 60.1, within the ±4.7 margin).
  • Claude Sonnet 5 (high) is stronger in coding, reasoning.
  • GPT-5.6 Terra (xhigh) is stronger in agents & tools, human preference, long context, maths, multimodal.
  • They cost about the same ($4.00 per 1M blended).

At a glance

SpecClaude Sonnet 5GPT-5.6 Terra
DeveloperAnthropicOpenAI
Released30 Jun 20269 Jul 2026
Context window (tokens)1,000,0001,050,000
Compared atClaude Sonnet 5 (high)GPT-5.6 Terra (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.200$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 (high)GPT-5.6 Terra (xhigh)Leader
Reasoning65.454.8Claude Sonnet 5
Coding59.959.1level
Agents & tools52.963.1GPT-5.6 Terra
Maths65.365.7level
Knowledge–53.0not comparable
Instruction following–65.6not comparable
Human preference64.665.5level
Multimodal60.961.2level
Long context62.964.1GPT-5.6 Terra

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 & toolsMathsLong contextMultimodalHumanpreferenceClaude Sonnet 5, Reasoning: 65.4Claude Sonnet 5, Coding: 59.9Claude Sonnet 5, Agents & tools: 52.9Claude Sonnet 5, Maths: 65.3Claude Sonnet 5, Long context: 62.9Claude Sonnet 5, Multimodal: 60.9Claude Sonnet 5, Human preference: 64.6GPT-5.6 Terra, Reasoning: 54.8GPT-5.6 Terra, Coding: 59.1GPT-5.6 Terra, Agents & tools: 63.1GPT-5.6 Terra, Maths: 65.7GPT-5.6 Terra, Long context: 64.1GPT-5.6 Terra, Multimodal: 61.2GPT-5.6 Terra, Human preference: 65.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 28 benchmarks both have, Claude Sonnet 5 leads 10, GPT-5.6 Terra leads 18. Every overall index that rates both puts GPT-5.6 Terra ahead.

Overall indexClaude Sonnet 5 (high)GPT-5.6 Terra (xhigh)Leader
BenchLeader Index59.060.1neck and neck
Arena Text14611468GPT-5.6 Terra

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 (high)GPT-5.6 Terra (xhigh)
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$0.200$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$0.079$0.087
Output speed99 tok/s97 tok/s
Time to first answer15.8 s19.2 s
Time to a complete answer, last measured 13 Nov 202640.7 s84.0 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 5 (high) scores 59.0 and takes 16 s to its first answer token; Claude Sonnet 5 (max) scores 56.1 in 158 s, Claude Sonnet 5 (xhigh) scores 55.4 in 32 s. GPT-5.6 Terra (xhigh) scores 60.1 and takes 19 s to its first answer token; GPT-5.6 Terra (max) scores 59.5 in 73 s, GPT-5.6 Terra (high) scores 56.8 in 6 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

146 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 (high)GPT-5.6 Terra (xhigh)
BenchLeader IndexBenchLeader59.060.1
Agents & tools scoreBenchLeader52.963.1
Coding scoreBenchLeader59.959.1
Human preference scoreBenchLeader64.665.5
Long context scoreBenchLeader62.964.1
Maths scoreBenchLeader65.365.7
Multimodal scoreBenchLeader60.961.2
Reasoning scoreBenchLeader65.454.8
Instruction following scoreBenchLeader–65.6
Knowledge scoreBenchLeader–53.0
Blended price $/MBenchLeader$4.00$4.50
Output speedBenchLeader99 tok/s97 tok/s
Time to first answerBenchLeader15.8 s19.2 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub80.3%†93.3%†
SimpleBenchSimpleBench60.6%†48.9%
Arena Hard PromptsArena (LMArena)14901491
LiveBench 2.0 ReasoningLiveBench–90.6%†
LiveBench 1.0 ReasoningLiveBench88.7%†90.6%†
GPQA Diamond (AA)Artificial Analysis91.1%†90.8%
Humanity's Last Exam (AA)Artificial Analysis35.7%41.9%
HLE-Diamond (AA)Artificial Analysis–24.7%
GPQA Diamond (Vals)Vals AI88.9%†90.9%
Kagi LLM BenchmarkKagi LLM Benchmark–51.3%†
ARC-AGI-1ARC Prize–94.0%
ARC-AGI-2ARC Prize–74.2%
ARC-AGI-3ARC Prize–0.7%
CritPtArtificial Analysis15.1%27.1%
CritPt v2 hard subset (AA)Artificial Analysis–50.5%†
Arena ExpertArena (LMArena)15091507
Chess PuzzlesEpoch AI Benchmarking Hub45.0%†47.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub16.0%†35.0%†
LMCAEpoch AI Benchmarking Hub50.0%52.2%
DTBenchEpoch AI Benchmarking Hub84.5%92.5%
ForecastBenchForecastBench63.1%†–
BTF-3Epoch AI Benchmarking Hub14.2%†–
Coding
SciCodeSciCode54.3%52.3%
WeirdMLWeirdML68.8%78.3%†
FrontierCodeCognition42.7%†41.3%†
Show all 146 benchmarks
MetricPublisherClaude Sonnet 5 (high)GPT-5.6 Terra (xhigh)
Coding
GSO-BenchGSO-Bench37.3%†–
Arena CodingArena (LMArena)15201517
Arena WebDevArena (LMArena)15391520
LiveBench 2.0 CodingLiveBench–84.2%†
LiveBench 1.0 CodingLiveBench80.7%†78.3%†
LiveCodeBenchVals AI82.4%†85.9%
IOIVals AI45.0%†87.6%†
SWE-bench (Vals)Vals AI79.6%†95.4%†
Code MigrationVals AI44.4%†47.8%†
ProgramBenchVals AI0.0%†0.5%†
Vibe Code Bench 1-100Vals AI13.8%†14.8%†
Vibe Code Bench v1.1Vals AI81.3%†74.6%†
SWE-Bench Pro V2Scale AI SEAL93.2%†92.4%
SWE-Bench Pro V2 HARDScale AI SEAL88.2%†86.3%
MirrorCodeEpoch AI Benchmarking Hub63.3%†41.1%†
Surface Evolver BenchEpoch AI Benchmarking Hub60.0%†83.8%
DeepSWE v1.1Epoch AI Benchmarking Hub48.2%60.2%
CursorBenchCursor30.8%33.6%
ALE-BenchEpoch AI Benchmarking Hub1463.11951.4†
Terminal-Bench 4.0 (AA)Artificial Analysis5.0%10.1%
Terminal-Bench 2.1 (AA)Artificial Analysis80.5%†80.2%
Startrise FrontendStartrise66.6%†66.9%†
GameBench 2 OverallDuelLab GameBench 246.6†45.6†
GameBench 2 by reasoning settingDuelLab GameBench 254.4†53.5
Design Arena WebsiteDesign Arena1268†1260†
FrontierCode 2.0 (AA)Artificial Analysis17.8%†23.9%†
Agents & tools
Terminal-BenchTerminal-Bench12.1%†21.5%†
APEX-AgentsMercor54.5%†58.2%†
Arena AgentArena (LMArena)2-1.8
LiveBench Long AgenticLiveBench–25.9%†
LiveBench BrowserLiveBench–70.3%†
LiveBench Agentic CodingLiveBench59.4%†55.0%†
Terminal-Bench HardArtificial Analysis–62.9%
τ²-Bench Telecom (AA)Artificial Analysis–80.4%
Terminal-Bench 2.1 (Vals)Vals AI74.5%†77.5%†
GDPval-AA v2.1, normalised scoreArtificial Analysis–47.4%
GDPval-AA v2.1Artificial Analysis12621456
τ³-Banking (AA)Artificial Analysis37.3%†29.7%
ITBench SRE (AA)Artificial Analysis–51.0%†
Analyst Agent (AA)Artificial Analysis46.3%†–
APEX-Agents (AA)Artificial Analysis–38.9%†
CyberBenchVals AI61.9%†72.1%†
Finance Agent v2Vals AI53.9%†54.4%†
Harvey's Legal Agent Benchmark v1Vals AI5.0%†0.8%†
Legal Research BenchVals AI41.8%†41.4%†
SkillsBenchVals AI46.5%†58.9%†
SREBenchVals AI0.4%†9.5%†
Tax Agent BenchVals AI29.4%†30.0%†
Terminal-Bench 4.0 (Vals)Vals AI10.6%†22.7%†
Terminal-Bench ScienceVals AI5.7%†10.0%†
Arena SearchArena (LMArena)1191†–
Arena Agent Task CompletionArena (LMArena)-0.6-7.2
BALROGBALROG–53.2%†
GBAEvalEpoch AI Benchmarking Hub65.3%†–
Vending-Bench 2Andon Labs6377.7†7343.2†
AutomationBenchArtificial Analysis32.1%47.1%
GDP.pdf (AA)Artificial Analysis9.4%24.6%
EnterpriseOps-GymArtificial Analysis44.7%†38.5%†
AA-Briefcase v1.1Artificial Analysis11771332
Design Arena AgenticDesign Arena1222†1089†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–13.8%†
DeepSec-Bench (AA)Artificial Analysis–25.1%†
FACTS SearchGoogle–87.0%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub65.6%†86.0%†
FrontierMath Tier 4Epoch AI Benchmarking Hub29.3%†70.7%†
OTIS Mock AIMEEpoch AI Benchmarking Hub80.0%†99.7%†
ProofBenchVals AI77.0%†74.0%
LiveBench MathematicsLiveBench92.9%†94.9%†
Arena MathsArena (LMArena)14721478
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub33.7%†43.2%†
LiveBench 2.0 Data AnalysisLiveBench–79.3%†
LiveBench ResearchLiveBench–79.7%†
LiveBench 1.0 Data AnalysisLiveBench71.7%†79.3%†
AA-Omniscience v1.1Artificial Analysis–-11.5
MMLU-ProVals AI87.5%†86.7%
LegalBenchVals AI83.9%†85.1%†
CorpFinVals AI67.0%†65.3%
TaxEvalVals AI75.6%†76.2%
Excel Modeling BenchmarkVals AI66.3%†66.2%†
MedCodeVals AI47.5%†43.4%
MedScribeVals AI76.0%†82.9%
Public Benefits Bench v1.1Vals AI66.0%†62.4%†
Financial Coaching BenchVals AI–71.0%†
DrugDiscoveryBenchScale AI SEAL50.0%†–
GDP.pdfEpoch AI Benchmarking Hub–24.7%†
AA-Omniscience v1.1: accuracyArtificial Analysis–41.3%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–9.9%
FACTS ParametricGoogle20.5%†57.6%†
Instruction following
LiveBench LanguageLiveBench75.0%†82.9%†
LiveBench Instruction FollowingLiveBench63.9%†64.6%†
IFBenchArtificial Analysis–66.3%
Arena Instruction FollowingArena (LMArena)14671463
Human preference
Arena TextArena (LMArena)14611468
EQ-Bench 4EQ-Bench1221†1220†
EQ-Bench Creative Writing v3EQ-Bench1798†1856†
Arena Creative WritingArena (LMArena)14341430
Arena Multi-turnArena (LMArena)14731475
Arena Longer QueriesArena (LMArena)14811469
Multimodal
Arena VisionArena (LMArena)12721269
LiveBench DesignLiveBench–70.9%†
MMMU-ProArtificial Analysis77.3%†79.5%
MMMU-Pro (Vals)Vals AI83.0%†86.5%†
MortgageTaxVals AI70.0%†67.3%
SAGEVals AI–87.0%†
Humanity's Sixth SenseScale AI SEAL24.8%†22.7%†
GeoBenchGeoBench74.0%–
Blueprint-Bench 2Epoch AI Benchmarking Hub24.9%†30.8%†
Furniture AssemblyEpoch AI Benchmarking Hub–54.2%†
FACTS MultimodalGoogle–39.9%†
Long context
AA-LCR v1.1Artificial Analysis76.7%79.0%
Arena DocumentArena (LMArena)14691474
MLCRArtificial Analysis4.4%22.8%
FACTS GroundingGoogle–60.5%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.9†160.7†
LiveBench 2.0LiveBench–67.2%†
LiveBench 1.0LiveBench76.0%†77.9%†
AA Intelligence Index v5.0.1Artificial Analysis–32.3†
AA Intelligence Index v4.3.2Artificial Analysis31.738.0
AA Progress Index v1Artificial Analysis296.8312
Vals Multimodal IndexVals AI68.8%†65.1%
Safety & honesty
DistressBenchScale AI SEAL68.0%†76.4%†

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Claude Sonnet 5 (high): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • GPT-5.6 Terra (xhigh): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • Claude Sonnet 5 (high): BenchLeader Index 59.5 → 59.0.
  • Claude Sonnet 5 (high): 1 new result (GeoBench).
  • Claude Sonnet 5 (high): 1 score revision.
  • GPT-5.6 Terra (xhigh): 1 score revision.
  • Claude Sonnet 5 (high): 1 score revision.
  • GPT-5.6 Terra (xhigh): 1 score revision.
  • GPT-5.6 Terra (xhigh): BenchLeader Index 61.2 → 60.4.
  • Claude Sonnet 5 (high): 1 new result (AA Progress Index v1).

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

Claude Sonnet 5 vs GPT-5.6 Terra: questions

Is Claude Sonnet 5 better than GPT-5.6 Terra?
Claude Sonnet 5 (high) and GPT-5.6 Terra (xhigh) are neck and neck on quality (59.0 vs 60.1, within the ±4.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Claude Sonnet 5 vs GPT-5.6 Terra: which is cheaper, and will that change?
Claude Sonnet 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 or GPT-5.6 Terra better for coding?
They are level in coding (60 vs 59 on the category index). On Arena WebDev, the top shared coding benchmark, it is 1539 for Claude Sonnet 5 against 1520 for GPT-5.6 Terra.
Which is faster, Claude Sonnet 5 or GPT-5.6 Terra?
Claude Sonnet 5 streams faster (99 vs 97 output tokens per second, Artificial Analysis 7-day median).
Is Claude Sonnet 5 or GPT-5.6 Terra better for agents and tool use?
GPT-5.6 Terra scores higher in agentic tasks (63 vs 53 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 2 for Claude Sonnet 5 against -1.8 for GPT-5.6 Terra.
More questions (4)
Which is better for long documents?
GPT-5.6 Terra scores higher on long-context benchmarks (64 vs 63). Both take about 1.1M tokens: Claude Sonnet 5 1,000,000, GPT-5.6 Terra 1,050,000.
Which has lower latency?
Claude Sonnet 5 answers first: 15.8 s against 19.2 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 vs GPT-5.6 Terra?
Across the 28 benchmarks both have, Claude Sonnet 5 leads 10, GPT-5.6 Terra leads 18. Every overall index that rates both puts GPT-5.6 Terra ahead.
When was GPT-5.6 Terra released?
GPT-5.6 Terra was released on 9 Jul 2026.