BenchLeader

GPT-5.3-Codex vs GPT-5.6 Sol

Full profiles: GPT-5.3-Codex (OpenAI) and GPT-5.6 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, GPT-5.3-Codex and GPT-5.6 Sol are neck and neck on quality (62.9 vs 65.3 on the BenchLeader Index, inside the ±7.7 margin), and GPT-5.3-Codex is 1.7× cheaper at $4.81 vs $8.00 per 1M tokens blended. Choose GPT-5.3-Codex for agents & tools (80 vs 68) and instruction following (74 vs 71); choose GPT-5.6 Sol for multimodal (66 vs 61) and coding (66 vs 61), where it also streams faster.

Key facts (as of 16 Nov 2026)

  • GPT-5.3-Codex scores 62.9 on the BenchLeader Index and GPT-5.6 Sol scores 65.3 (BenchLeader, 16 Nov 2026).
  • GPT-5.3-Codex costs $4.81 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-5.6 Sol costs $8.00 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-5.6 Sol streams faster than GPT-5.3-Codex (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 16 benchmarks both models have, GPT-5.6 Sol leads 13 (BenchLeader, 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
CodingGPT-5.6 Sol66 vs 61 category score; WeirdML 87.0% vs 77.9%Medium
Agents & tool useGPT-5.3-Codex80 vs 68 category score; Terminal-Bench Hard 53.0% vs 65.9%High
Long documentsEither66 vs 67 category score; AA-LCR v1.1 83.3% vs 84.0%Either
Images and other mediaGPT-5.6 Sol66 vs 61 category score; MMMU-Pro 83.4% vs 78.5%Medium
Following instructionsGPT-5.3-Codex74 vs 71 category score; IFBench 75.4% vs 72.7%Medium
Lowest costGPT-5.3-Codex$4.81 vs $8.00 per 1M blended; agentic coding session $0.161 vs $0.320–
Fastest first answerEither38.2 s (GPT-5.3-Codex (xhigh)) vs 33.5 s (GPT-5.6 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

  • GPT-5.3-Codex (xhigh) and GPT-5.6 Sol (max) are neck and neck on quality (62.9 vs 65.3, within the ±7.7 margin).
  • GPT-5.3-Codex (xhigh) is stronger in agents & tools, instruction following.
  • GPT-5.6 Sol (max) is stronger in coding, long context, multimodal.
  • GPT-5.3-Codex (xhigh) is 1.7× cheaper ($4.81 vs $8.00 per 1M blended).

At a glance

SpecGPT-5.3-CodexGPT-5.6 Sol
DeveloperOpenAIOpenAI
Released5 Feb 20269 Jul 2026
Context window (tokens)400,0001,050,000
Compared atGPT-5.3-Codex (xhigh)GPT-5.6 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$1.75 / $14.00 / $0.175$4.00 / $20.00 / $0.400

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.

CategoryGPT-5.3-Codex (xhigh)GPT-5.6 Sol (max)Leader
Reasoning–64.7not comparable
Coding61.065.8GPT-5.6 Sol
Agents & tools80.167.5GPT-5.3-Codex
Maths–70.0not comparable
Knowledge–63.8not comparable
Instruction following73.671.2GPT-5.3-Codex
Multimodal60.865.9GPT-5.6 Sol
Long context66.466.7level

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 avg75CodingAgents & toolsInstructionfollowingLong contextMultimodalGPT-5.3-Codex, Coding: 61.0GPT-5.3-Codex, Agents & tools: 80.1GPT-5.3-Codex, Instruction following: 73.6GPT-5.3-Codex, Long context: 66.4GPT-5.3-Codex, Multimodal: 60.8GPT-5.6 Sol, Coding: 65.8GPT-5.6 Sol, Agents & tools: 67.5GPT-5.6 Sol, Instruction following: 71.2GPT-5.6 Sol, Long context: 66.7GPT-5.6 Sol, Multimodal: 65.9

Not drawn, measured for fewer than two of these models: Reasoning, Maths, Knowledge, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 16 benchmarks both have, GPT-5.3-Codex leads 3, GPT-5.6 Sol leads 13.

Overall indexGPT-5.3-Codex (xhigh)GPT-5.6 Sol (max)Leader
BenchLeader Index62.965.3neck and neck

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.

MeasureGPT-5.3-Codex (xhigh)GPT-5.6 Sol (max)
Blended price per 1M tokens$4.81$8.00
Input / output per 1M$1.75 / $14.00$4.00 / $20.00
Cached input per 1M$0.175$0.400
Price per task: chat reply$0.0049$0.0076
Price per task: summarize a 30-page report$0.029$0.060
Price per task: code edit$0.032$0.054
Price per task: agentic coding session$0.161$0.320
Price per task: structured extraction$0.0063$0.012
Agentic coding session, input mostly cached$0.090$0.158
Output speed94 tok/s100 tok/s
Time to first answer38.2 s33.5 s
Time to a complete answer, last measured 13 Nov 202697.1 s157.3 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.3-Codex (xhigh) scores 62.9 and takes 38 s to its first answer token. GPT-5.6 Sol (max) scores 65.3 and takes 34 s to its first answer token; GPT-5.6 Sol (xhigh) scores 63.9 in 17 s, GPT-5.6 Sol (high) scores 63.4 in 10 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

153 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.

MetricPublisherGPT-5.3-Codex (xhigh)GPT-5.6 Sol (max)
BenchLeader IndexBenchLeader62.965.3
Agents & tools scoreBenchLeader80.167.5
Coding scoreBenchLeader61.065.8
Instruction following scoreBenchLeader73.671.2
Long context scoreBenchLeader66.466.7
Multimodal scoreBenchLeader60.865.9
Knowledge scoreBenchLeader–63.8
Maths scoreBenchLeader–70.0
Reasoning scoreBenchLeader–64.7
Blended price $/MBenchLeader$4.81$8.00
Output speedBenchLeader94 tok/s100 tok/s
Time to first answerBenchLeader38.2 s33.5 s
Context windowBenchLeader400,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–93.5%
SimpleBenchSimpleBench–64.8%†
Arena Hard PromptsArena (LMArena)–1511†
LiveBench 1.0 ReasoningLiveBench–91.7%
GPQA Diamond (AA)Artificial Analysis91.5%94.1%
Humanity's Last Exam (AA)Artificial Analysis42.5%49.5%
GPQA Diamond (Vals)Vals AI–95.2%
EnigmaEvalScale AI SEAL–37.1%†
Kagi LLM BenchmarkKagi LLM Benchmark–67.0%†
ARC-AGI-1ARC Prize–96.5%
ARC-AGI-2ARC Prize–92.5%
ARC-AGI-3ARC Prize–7.8%
CritPtArtificial Analysis16.9%32.3%
CritPt v2 hard subset (AA)Artificial Analysis–60.0%
MysteryMechanismVals AI–33.3%
HLE-Diamond (Scale)Scale AI SEAL–31.2%†
Arena ExpertArena (LMArena)–1532†
Chess PuzzlesEpoch AI Benchmarking Hub–59.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub–58.0%
LMCAEpoch AI Benchmarking Hub–58.4%
DTBenchEpoch AI Benchmarking Hub–95.5%
ForecastBenchForecastBench–65.7%
BTF-3Epoch AI Benchmarking Hub–13.7%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub74.8%†–
SciCodeSciCode–57.1%
Show all 153 benchmarks
MetricPublisherGPT-5.3-Codex (xhigh)GPT-5.6 Sol (max)
Coding
WeirdMLWeirdML77.9%87.0%
FrontierCodeCognition–47.5%†
GSO-BenchGSO-Bench–76.5%†
Arena CodingArena (LMArena)–1533†
Arena WebDevArena (LMArena)1406†1615†
LiveBench 1.0 CodingLiveBench–83.9%
LiveCodeBenchVals AI87.3%82.6%
IOIVals AI53.8%91.2%
SWE-bench (Vals)Vals AI78.0%96.2%
Code MigrationVals AI–52.9%
ProgramBenchVals AI–1.5%
Vibe Code Bench 1-100Vals AI–20.0%
Vibe Code Bench v1.1Vals AI61.8%80.5%
SWE Atlas v1.0: Codebase QnAScale AI SEAL–46.0%†
SWE Atlas v1.0: Test WritingScale AI SEAL–45.9%†
SWE-Bench Pro V2Scale AI SEAL–95.5%†
SWE-Bench Pro V2 HARDScale AI SEAL–82.4%†
MirrorCodeEpoch AI Benchmarking Hub–20.0%†
Surface Evolver BenchEpoch AI Benchmarking Hub–93.1%†
DeepSWE v1.1Epoch AI Benchmarking Hub–72.7%
CursorBenchCursor–41.7%
ALE-BenchEpoch AI Benchmarking Hub1655.22176.9
FrontierSWEEpoch AI Benchmarking Hub–32.2%
WeirdML v3WeirdML–15.0%†
Terminal-Bench 4.0 (AA)Artificial Analysis–39.9%
Terminal-Bench 2.1 (AA)Artificial Analysis–88.0%
Startrise FrontendStartrise–66.2%†
GameBench 2 OverallDuelLab GameBench 2–67.0†
GameBench 2 by reasoning settingDuelLab GameBench 2–80.0†
Design Arena WebsiteDesign Arena1155†1319†
Agents & tools
Terminal-BenchTerminal-Bench78.4%†38.5%
OSWorld-Verified 2.0OSWorld–27.3%
APEX-AgentsMercor–51.4%†
Arena AgentArena (LMArena)–4.6†
LiveBench Agentic CodingLiveBench–56.2%
Terminal-Bench HardArtificial Analysis53.0%65.9%
τ²-Bench Telecom (AA)Artificial Analysis86.0%85.1%
Terminal-Bench 2.1 (Vals)Vals AI–85.8%
HiL-BenchScale AI SEAL4.3%†32.3%†
τ³-bench Bankingτ²-bench–46.9%†
GDPval-AA v2.1Artificial Analysis–1619
τ³-Banking (AA)Artificial Analysis–44.3%
ITBench SRE (AA)Artificial Analysis–56.2%
Analyst Agent (AA)Artificial Analysis–47.5%
CUA-benchVals AI–8.3%
CyberBenchVals AI–76.3%
Finance Agent v2Vals AI–53.8%
Harvey's Legal Agent Benchmark v1Vals AI–2.5%
Legal Research BenchVals AI–48.1%
SkillsBenchVals AI–54.1%
SREBenchVals AI–30.5%
Tax Agent BenchVals AI–31.1%
Terminal-Bench 2.0 (Vals)Vals AI64.0%†–
Terminal-Bench 4.0 (Vals)Vals AI–37.9%
Terminal-Bench ScienceVals AI–20.0%
Time Horizon Index: KSPVals AI–23.8%
Web Search IndexVals AI–43.6%
Arena SearchArena (LMArena)–1255†
Arena Agent Task CompletionArena (LMArena)–2.3†
BALROGBALROG–60.0%
PostTrainBenchEpoch AI Benchmarking Hub–31.0%
METR Time HorizonsMETR74.5%†–
GBAEvalEpoch AI Benchmarking Hub–52.6%†
Vending-Bench 2Andon Labs5940.1†9619.4†
AutomationBenchArtificial Analysis–60.1%
GDP.pdf (AA)Artificial Analysis–27.2%
EnterpriseOps-GymArtificial Analysis–42.9%
AA-Briefcase v1.1Artificial Analysis8681479
Design Arena AgenticDesign Arena1018†1238†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–22.4%
FACTS SearchGoogle–92.9%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–89.1%
FrontierMath Tier 4Epoch AI Benchmarking Hub–82.9%
OTIS Mock AIMEEpoch AI Benchmarking Hub–100.0%
ProofBenchVals AI–83.0%
LiveBench MathematicsLiveBench–96.2%
Arena MathsArena (LMArena)–1494†
FrontierMath ErdősEpoch AI Benchmarking Hub–0.0%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–69.7%
LiveBench 1.0 Data AnalysisLiveBench–79.8%
MMLU-ProVals AI–89.1%
LegalBenchVals AI–87.0%
CorpFinVals AI–64.4%
TaxEvalVals AI–74.8%
PRBench FinanceScale AI SEAL–50.5%
PRBench LegalScale AI SEAL–50.5%
BioMysteryBenchVals AI–71.1%
Excel Modeling BenchmarkVals AI–72.3%
MedCodeVals AI–44.0%
MedScribeVals AI–85.2%
Public Benefits Bench v1.1Vals AI–66.5%
Financial Coaching BenchVals AI–74.9%
DrugDiscoveryBenchScale AI SEAL–56.5%
EBR-benchEpoch AI Benchmarking Hub–44.8%
GDP.pdfEpoch AI Benchmarking Hub–30.7%
FACTS ParametricGoogle–81.1%†
Instruction following
LiveBench LanguageLiveBench–87.7%
LiveBench Instruction FollowingLiveBench–71.8%
IFBenchArtificial Analysis75.4%72.7%
Arena Instruction FollowingArena (LMArena)–1490†
Human preference
Arena TextArena (LMArena)–1485†
EQ-Bench 4EQ-Bench–1236†
EQ-Bench Creative Writing v3EQ-Bench–1974†
Arena Creative WritingArena (LMArena)–1471†
Arena Multi-turnArena (LMArena)–1491†
Arena Longer QueriesArena (LMArena)–1498†
Multimodal
Arena VisionArena (LMArena)–1282†
MMMU-ProArtificial Analysis78.5%83.4%
MMMU-Pro (Vals)Vals AI–88.8%
MortgageTaxVals AI–67.3%
Humanity's Sixth SenseScale AI SEAL–30.0%
GeoBenchGeoBench–73.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub–33.6%†
Furniture AssemblyEpoch AI Benchmarking Hub–56.7%
FACTS MultimodalGoogle–46.4%†
Long context
AA-LCR v1.1Artificial Analysis83.3%84.0%
Arena DocumentArena (LMArena)–1487†
MLCRArtificial Analysis–30.0%
FACTS GroundingGoogle–61.9%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–163.0†
LiveBench 1.0LiveBench–81.0%
AA Intelligence Index v4.3.2Artificial Analysis32.547.0
AA Progress Index v1Artificial Analysis301.3331.5
Vals RSI IndexVals AI–23.9%
Vals Science IndexVals AI–41.5%
Vals Multimodal IndexVals AI–72.6%
Safety & honesty
FORTRESSScale AI SEAL–20.1%†
DistressBenchScale AI SEAL–73.6%†

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

  • GPT-5.6 Sol (max): 1 new result (GDPval-AA v2.1).
  • GPT-5.6 Sol (max): 1 score revision.
  • GPT-5.6 Sol (max): BenchLeader Index 65.8 → 65.3.
  • GPT-5.6 Sol (max): 1 score revision.
  • GPT-5.6 Sol (max): 1 score revision.
  • GPT-5.3-Codex (xhigh): 1 new result (AA-Briefcase v1.1).
  • GPT-5.3-Codex (xhigh): 1 new result (AA Progress Index v1).
  • GPT-5.6 Sol (max): 2 new results (AA Progress Index v1, CritPt v2 hard subset (AA)).
  • GPT-5.6 Sol (max): 1 new result (AA-Briefcase v1.1).
  • GPT-5.6 Sol (max): 3 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index, Vals Science Index).

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

GPT-5.3-Codex vs GPT-5.6 Sol: questions

Is GPT-5.3-Codex better than GPT-5.6 Sol?
GPT-5.3-Codex (xhigh) and GPT-5.6 Sol (max) are neck and neck on quality (62.9 vs 65.3, within the ±7.7 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.
GPT-5.3-Codex vs GPT-5.6 Sol: which is cheaper, and will that change?
GPT-5.3-Codex is cheaper today: $4.81 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.3-Codex or GPT-5.6 Sol better for coding?
GPT-5.6 Sol scores higher in coding (66 vs 61 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 87.3% for GPT-5.3-Codex against 82.6% for GPT-5.6 Sol.
Which is faster, GPT-5.3-Codex or GPT-5.6 Sol?
GPT-5.6 Sol streams faster (100 vs 94 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.3-Codex or GPT-5.6 Sol better for agents and tool use?
GPT-5.3-Codex scores higher in agentic tasks (80 vs 68 on the category index, where 50 is average). On Terminal-Bench Hard, the top shared agents & tools benchmark, it is 53.0% for GPT-5.3-Codex against 65.9% for GPT-5.6 Sol.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (66 vs 67). GPT-5.6 Sol accepts more context: 1,050,000 against 400,000 tokens for GPT-5.3-Codex.
Which has lower latency?
GPT-5.6 Sol answers first: 33.5 s against 38.2 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 GPT-5.3-Codex vs GPT-5.6 Sol?
Across the 16 benchmarks both have, GPT-5.3-Codex leads 3, GPT-5.6 Sol leads 13.
When was GPT-5.6 Sol released?
GPT-5.6 Sol was released on 9 Jul 2026.