BenchLeader

GPT-5.2-Codex vs GPT-6 Sol

Full profiles: GPT-5.2-Codex (OpenAI) and GPT-6 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 14 sources

As of 16 Nov 2026, GPT-5.2-Codex and GPT-6 Sol are neck and neck on quality (57.6 vs 62.6 on the BenchLeader Index, inside the ±10.5 margin), and GPT-6 Sol is 1.2× cheaper at $4.00 vs $4.81 per 1M tokens blended. Choose GPT-5.2-Codex for agents & tools (69 vs 59) and fast first answers (1.5 s vs 36.9 s); choose GPT-6 Sol for coding (66 vs 55), where it also streams ~2× faster.

Key facts (as of 16 Nov 2026)

  • GPT-5.2-Codex scores 57.6 on the BenchLeader Index and GPT-6 Sol scores 62.6 (BenchLeader, 16 Nov 2026).
  • GPT-5.2-Codex costs $4.81 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-6 Sol streams ~2× faster than GPT-5.2-Codex (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 11 benchmarks both models have, GPT-6 Sol leads 9 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, GPT-5.2-Codex is rated 1339 and GPT-6 Sol 1673 (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
CodingGPT-6 Sol66 vs 55 category score; Arena WebDev 1673 vs 1339High
Agents & tool useGPT-5.2-Codex69 vs 59 category score; Terminal-Bench 66.5% vs 50.3%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 $4.81 per 1M blended; agentic coding session $0.160 vs $0.161–
Fastest first answerGPT-5.2-Codex1.5 s (GPT-5.2-Codex) vs 36.9 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

  • GPT-5.2-Codex and GPT-6 Sol (max) are neck and neck on quality (57.6 vs 62.6, within the ±10.5 margin).
  • GPT-5.2-Codex is stronger in agents & tools.
  • GPT-6 Sol (max) is stronger in coding.
  • GPT-6 Sol (max) is 1.2× cheaper ($4.00 vs $4.81 per 1M blended).
  • GPT-6 Sol (max) streams 2.8× faster (127 vs 45 tokens per second).

At a glance

SpecGPT-5.2-CodexGPT-6 Sol
DeveloperOpenAIOpenAI
Released18 Dec 202522 Sep 2026
Context window (tokens)272,0001,050,000
Compared atGPT-5.2-CodexGPT-6 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$1.75 / $14.00 / $0.175$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.

CategoryGPT-5.2-CodexGPT-6 Sol (max)Leader
Reasoning–66.0not comparable
Coding55.266.3GPT-6 Sol
Agents & tools69.058.8GPT-5.2-Codex
Maths–68.0not comparable
Knowledge–60.6not comparable
Human preference–64.2not comparable
Multimodal–60.6not 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 & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceGPT-5.2-Codex, Coding: 55.2GPT-5.2-Codex, Agents & tools: 69.0GPT-6 Sol, Reasoning: 66.0GPT-6 Sol, Coding: 66.3GPT-6 Sol, Agents & tools: 58.8GPT-6 Sol, Maths: 68.0GPT-6 Sol, Knowledge: 60.6GPT-6 Sol, Long context: 66.6GPT-6 Sol, Multimodal: 60.6GPT-6 Sol, Human preference: 64.2

Dashed: that model has no result on the axis it crosses; the line only joins its neighbours.

Not drawn, no result for these models: Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 11 benchmarks both have, GPT-5.2-Codex leads 2, GPT-6 Sol leads 9.

Overall indexGPT-5.2-CodexGPT-6 Sol (max)Leader
BenchLeader Index57.662.6neck 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-5.2-CodexGPT-6 Sol (max)
Blended price per 1M tokens$4.81$4.00
Input / output per 1M$1.75 / $14.00$2.00 / $10.00
Cached input per 1M$0.175$0.200
Price per task: chat reply$0.0049$0.0038
Price per task: summarize a 30-page report$0.029$0.030
Price per task: code edit$0.032$0.027
Price per task: agentic coding session$0.161$0.160
Price per task: structured extraction$0.0063$0.0060
Agentic coding session, input mostly cached$0.090$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 speed45 tok/s127 tok/s
Time to first answer1.5 s36.9 s
Time to a complete answer, last measured 13 Nov 2026–143.8 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.2-Codex scores 57.6 and takes 1 s to its first answer token. GPT-6 Sol (max) scores 62.6 and takes 37 s to its first answer token; GPT-6 Sol (xhigh) scores 58.4 in 19 s, GPT-6 Sol (high) scores 58.1 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

126 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-5.2-CodexGPT-6 Sol (max)
BenchLeader IndexBenchLeader57.662.6
Agents & tools scoreBenchLeader69.058.8
Coding scoreBenchLeader55.266.3
Human preference scoreBenchLeader–64.2
Knowledge scoreBenchLeader–60.6
Long context scoreBenchLeader–66.6
Maths scoreBenchLeader–68.0
Multimodal scoreBenchLeader–60.6
Reasoning scoreBenchLeader–66.0
Blended price $/MBenchLeader$4.81$4.00
Output speedBenchLeader45 tok/s127 tok/s
Time to first answerBenchLeader1.5 s36.9 s
Context windowBenchLeader272,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–94.3%
SimpleBenchSimpleBench–73.1%†
Arena Hard PromptsArena (LMArena)–1483
LiveBench 1.0 ReasoningLiveBench77.7%88.7%
GPQA Diamond (AA)Artificial Analysis89.9%†–
Humanity's Last Exam (AA)Artificial Analysis35.7%†47.9%
HLE-Diamond (AA)Artificial Analysis–45.2%
ARC-AGI-1ARC Prize–95.5%
ARC-AGI-2ARC Prize–89.6%
ARC-AGI-3ARC Prize–23.0%
CritPtArtificial Analysis8.7%†30.9%
CritPt v2 hard subset (AA)Artificial Analysis–66.5%
MysteryMechanismVals AI–30.2%
HLE-Diamond (Scale)Scale AI SEAL–33.8%†
Arena ExpertArena (LMArena)–1496
Chess PuzzlesEpoch AI Benchmarking Hub–56.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub–56.0%
LMCAEpoch AI Benchmarking Hub–59.1%
DTBenchEpoch AI Benchmarking Hub–97.3%
Coding
SciCodeSciCode–57.6%
FrontierCodeCognition–49.3%
Arena CodingArena (LMArena)–1521
Arena WebDevArena (LMArena)13391673
LiveBench 1.0 CodingLiveBench83.6%81.8%
LiveCodeBenchVals AI88.0%–
Show all 126 benchmarks
MetricPublisherGPT-5.2-CodexGPT-6 Sol (max)
Coding
IOIVals AI–82.6%
SWE-bench (Vals)Vals AI72.4%†–
SWE-Bench ProScale AI SEAL41.0%–
SWE-bench Verified (bash only)SWE-bench72.8%–
SWE-bench Multilingual (bash only)SWE-bench66.3%–
SWE-bench Verified (any scaffold)SWE-bench72.8%–
Code MigrationVals AI–57.2%
ProgramBenchVals AI–2.0%
Vibe Code Bench v1.1Vals AI37.9%†87.8%
SWE-Bench Pro (private)Scale AI SEAL27.7%–
MirrorCodeEpoch AI Benchmarking Hub–48.9%
ALE-BenchEpoch AI Benchmarking Hub1299.92462
WeirdML v3WeirdML–19.7%†
Terminal-Bench 4.0 (AA)Artificial Analysis–43.9%
GameBench 2 OverallDuelLab GameBench 2–73.0†
GameBench 2 by reasoning settingDuelLab GameBench 2–79.4†
Design Arena WebsiteDesign Arena–1290†
FrontierCode 2.0 (AA)Artificial Analysis–35.6%
Agents & tools
Terminal-BenchTerminal-Bench66.5%50.3%
APEX-AgentsMercor–54.3%
Arena AgentArena (LMArena)–6.9
LiveBench Agentic CodingLiveBench49.4%52.9%
Terminal-Bench HardArtificial Analysis37.1%†–
τ²-Bench Telecom (AA)Artificial Analysis92.1%†–
Terminal-Bench 2.1 (Vals)Vals AI–83.2%
GDPval-AA v2.1Artificial Analysis–1514
ITBench SRE (AA)Artificial Analysis–49.4%
CyberBenchVals AI–78.0%
Finance Agent v2Vals AI–49.0%
Harvey's Legal Agent Benchmark v1Vals AI–1.7%
Legal Research BenchVals AI–28.9%
SREBenchVals AI–30.5%
Tax Agent BenchVals AI–15.0%
Terminal-Bench 4.0 (Vals)Vals AI–44.4%
Terminal-Bench ScienceVals AI–30.0%
Arena SearchArena (LMArena)–1229
Arena Agent Task CompletionArena (LMArena)–4.5
Vending-Bench 2Andon Labs–14427.9†
SpireClimbEpoch AI Benchmarking Hub–9.2%
AutomationBenchArtificial Analysis–61.6%
GDP.pdf (AA)Artificial Analysis–25.2%
Harvey LAB-AA v1.1Harvey–3.6%
AA-Briefcase v1.1Artificial Analysis–1476
Design Arena AgenticDesign Arena10391218†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–30.0%
CWE-Bench (AA)Artificial Analysis–64.2%
DeepSec-Bench (AA)Artificial Analysis–46.3%
CyberGym end-to-end (AA)Artificial Analysis–0.0%
FACTS SearchGoogle–92.7%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–89.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub–90.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub–100.0%
ProofBenchVals AI–83.0%†
LiveBench MathematicsLiveBench88.8%96.4%
Arena MathsArena (LMArena)–1440
FrontierMath ErdősEpoch AI Benchmarking Hub–1.5%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–60.7%
LiveBench 1.0 Data AnalysisLiveBench78.2%81.2%
AA-Omniscience v1.1Artificial Analysis–21.4
PRBench LegalScale AI SEAL–38.6%†
BioMysteryBenchVals AI–74.8%
Excel Modeling BenchmarkVals AI–71.5%
MedCodeVals AI–47.1%
MedScribeVals AI–82.0%
Public Benefits Bench v1.1Vals AI–56.6%
Financial Coaching BenchVals AI–62.6%
EBR-benchEpoch AI Benchmarking Hub–53.3%
GDP.pdfEpoch AI Benchmarking Hub–26.4%
AA-Omniscience v1.1: accuracyArtificial Analysis–51.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–39.1%
HealthBench Professional (AA)OpenAI–62.3%
FACTS ParametricGoogle–76.1%†
Instruction following
LiveBench LanguageLiveBench73.7%85.3%
LiveBench Instruction FollowingLiveBench66.5%68.6%
IFBenchArtificial Analysis77.6%†–
Arena Instruction FollowingArena (LMArena)–1449
Human preference
Arena TextArena (LMArena)–1457
EQ-Bench Creative Writing v3EQ-Bench–2126†
Arena Creative WritingArena (LMArena)–1428
Arena Multi-turnArena (LMArena)–1468
Arena Longer QueriesArena (LMArena)–1466
Multimodal
Arena VisionArena (LMArena)–1233
MMMU-ProArtificial Analysis76.3%†83.0%
Humanity's Sixth SenseScale AI SEAL–31.2%
Blueprint-Bench 2Epoch AI Benchmarking Hub–36.9%†
Furniture AssemblyEpoch AI Benchmarking Hub–58.3%
AA-3DArtificial Analysis–1131
FACTS MultimodalGoogle–43.9%†
Long context
AA-LCR v1.1Artificial Analysis82.3%†83.7%
MLCRArtificial Analysis–33.9%
FACTS GroundingGoogle–83.3%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–163.8†
LiveBench 1.0LiveBench74.0%79.3%
AA Intelligence Index v5.0.1Artificial Analysis–44.2
AA Intelligence Index v4.3.2Artificial Analysis28.5†47.6
AA Progress Index v1Artificial Analysis290.2†334
Vals RSI IndexVals AI–28.1%
Vals Science IndexVals AI–45.0%
AA Cyber IndexArtificial Analysis–36.8
Safety & honesty
FORTRESSScale AI SEAL–13.5%†
DistressBenchScale AI SEAL–68.0%†

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-6 Sol (max): 1 new result (GDPval-AA v2.1).
  • GPT-6 Sol (max): 1 new result (MirrorCode).
  • GPT-6 Sol (max): BenchLeader Index 63.5 → 62.9.
  • GPT-6 Sol (max): 2 score revisions.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 6 new results (AA Intelligence Index v5.0.1, AA-Omniscience v1.1, CritPt v2 hard subset (AA)…).
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): BenchLeader Index 64.1 → 63.5.

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

GPT-5.2-Codex vs GPT-6 Sol: questions

Is GPT-5.2-Codex better than GPT-6 Sol?
GPT-5.2-Codex and GPT-6 Sol (max) are neck and neck on quality (57.6 vs 62.6, within the ±10.5 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-5.2-Codex vs GPT-6 Sol: which is cheaper, and will that change?
GPT-6 Sol is cheaper today: $4.00 against $4.81 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.2-Codex or GPT-6 Sol better for coding?
GPT-6 Sol scores higher in coding (66 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1339 for GPT-5.2-Codex against 1673 for GPT-6 Sol.
Which is faster, GPT-5.2-Codex or GPT-6 Sol?
GPT-6 Sol streams ~2× faster (127 vs 45 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.2-Codex or GPT-6 Sol better for agents and tool use?
GPT-5.2-Codex scores higher in agentic tasks (69 vs 59 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 66.5% for GPT-5.2-Codex against 50.3% for GPT-6 Sol.
More questions (4)
Which is better for long documents?
GPT-6 Sol accepts more context: 1,050,000 against 272,000 tokens for GPT-5.2-Codex.
Which has lower latency?
GPT-5.2-Codex answers first: 1.5 s against 36.9 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-5.2-Codex vs GPT-6 Sol?
Across the 11 benchmarks both have, GPT-5.2-Codex leads 2, GPT-6 Sol leads 9.
When was GPT-6 Sol released?
GPT-6 Sol was released on 22 Sep 2026.