BenchLeader

GPT-6.2 Sol vs GPT-6 Sol

Full profiles: GPT-6.2 Sol (OpenAI) and GPT-6 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 11 sources

As of 19 Nov 2026, GPT-6.2 Sol and GPT-6 Sol are neck and neck on quality (64.6 vs 62.4 on the BenchLeader Index, inside the ±3.7 margin), and they cost about the same at $4.00 vs $4.00 per 1M tokens blended. GPT-6.2 Sol leads in every category we measure both in. GPT-6 Sol streams faster.

Key facts (as of 19 Nov 2026)

  • GPT-6.2 Sol scores 64.6 on the BenchLeader Index and GPT-6 Sol scores 62.4 (BenchLeader, 19 Nov 2026).
  • GPT-6.2 Sol costs $4.00 per 1M tokens blended (list price, 19 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 19 Nov 2026).
  • GPT-6 Sol streams faster than GPT-6.2 Sol (Artificial Analysis, 7-day median, 19 Nov 2026).
  • Of the 33 benchmarks both models have, GPT-6.2 Sol leads 28 (BenchLeader, 19 Nov 2026).
  • On Arena WebDev, GPT-6.2 Sol is rated 1757 and GPT-6 Sol 1674 (LMArena, as published by 19 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-6.2 Sol75 vs 66 category score; Arena WebDev 1757 vs 1674High
Agents & tool useGPT-6.2 Sol65 vs 60 category score; Terminal-Bench 61.5% vs 50.3%Medium
ReasoningGPT-6.2 Sol70 vs 65 category score; HLE-Diamond (AA) 64.0% vs 45.2%Medium
KnowledgeGPT-6.2 Sol65 vs 60 category score; AA-Omniscience v1.1 40.4 vs 21.4Medium
Chat quality (human preference)–Only GPT-6 Sol has an Arena rating (64 category score)Not comparable
Lowest costEither$4.00 vs $4.00 per 1M blended; agentic coding session $0.160 vs $0.160–
Fastest first answerGPT-6 Sol39.1 s (GPT-6 Sol (max)) vs 78.8 s (GPT-6.2 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-6.2 Sol (max) and GPT-6 Sol (max) are neck and neck on quality (64.6 vs 62.4, within the ±3.7 margin).
  • GPT-6.2 Sol (max) is stronger in agents & tools, coding, knowledge, reasoning.
  • They cost about the same ($4.00 per 1M blended).
  • GPT-6 Sol (max) streams 1.6× faster (115 vs 74 tokens per second).

At a glance

SpecGPT-6.2 SolGPT-6 Sol
DeveloperOpenAIOpenAI
Released17 Nov 202622 Sep 2026
Context window (tokens)1,050,0001,050,000
Compared atGPT-6.2 Sol (max)GPT-6 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.100$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-6.2 Sol (max)GPT-6 Sol (max)Leader
Reasoning70.164.9GPT-6.2 Sol
Coding74.565.5GPT-6.2 Sol
Agents & tools65.160.3GPT-6.2 Sol
Maths–67.8not comparable
Knowledge65.459.9GPT-6.2 Sol
Human preference–64.2not comparable
Multimodal–60.5not comparable
Long context–66.6not comparable
Composite64.5–not 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 & toolsKnowledgeGPT-6.2 Sol, Reasoning: 70.1GPT-6.2 Sol, Coding: 74.5GPT-6.2 Sol, Agents & tools: 65.1GPT-6.2 Sol, Knowledge: 65.4GPT-6 Sol, Reasoning: 64.9GPT-6 Sol, Coding: 65.5GPT-6 Sol, Agents & tools: 60.3GPT-6 Sol, Knowledge: 59.9

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

Model, click to add or removeIndex

Where sources disagree

Across the 33 benchmarks both have, GPT-6.2 Sol leads 28, GPT-6 Sol leads 4 and 1 is a tie. Every overall index that rates both puts GPT-6.2 Sol ahead.

Overall indexGPT-6.2 Sol (max)GPT-6 Sol (max)Leader
BenchLeader Index64.662.4neck and neck
AA Intelligence Index v5.0.157.344.2GPT-6.2 Sol

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-6.2 Sol (max)GPT-6 Sol (max)
Blended price per 1M tokens$4.00$4.00
Input / output per 1M$2.00 / $10.00$2.00 / $10.00
Cached input per 1M$0.100$0.200
Price per task: chat reply$0.0038$0.0038
Price per task: summarize a 30-page report$0.030$0.030
Price per task: code edit$0.027$0.027
Price per task: agentic coding session$0.160$0.160
Price per task: structured extraction$0.0060$0.0060
Agentic coding session, input mostly cached$0.074$0.079
Cost per benchmark task (AA Index)$1.01$2.47
Output tokens per task (AA Index)40k54k
Of which reasoning23k35k
Time per task (AA Index)9 min8 min
Output speed74 tok/s115 tok/s
Time to first answer78.8 s39.1 s
Time to a complete answer, last measured 13 Nov 2026–143.8 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $1.01 on GPT-6.2 Sol (max) and $2.47 on GPT-6 Sol (max), and GPT-6 Sol (max) wrote 1.3× 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. GPT-6.2 Sol (max) scores 64.6 and takes 79 s to its first answer token; GPT-6.2 Sol (xhigh) scores 63.3 in 32 s, GPT-6.2 Sol (high) scores 62.3 in 12 s. GPT-6 Sol (max) scores 62.4 and takes 39 s to its first answer token; GPT-6 Sol (xhigh) scores 58.2 in 14 s, GPT-6 Sol (high) scores 57.8 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

141 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-6.2 Sol (max)GPT-6 Sol (max)
BenchLeader IndexBenchLeader64.662.4
Agents & tools scoreBenchLeader65.160.3
Coding scoreBenchLeader74.565.5
Composite scoreBenchLeader64.5–
Knowledge scoreBenchLeader65.459.9
Reasoning scoreBenchLeader70.164.9
Human preference scoreBenchLeader–64.2
Long context scoreBenchLeader–66.6
Maths scoreBenchLeader–67.8
Multimodal scoreBenchLeader–60.5
Blended price $/MBenchLeader$4.00$4.00
Output speedBenchLeader74 tok/s115 tok/s
Time to first answerBenchLeader78.8 s39.1 s
Context windowBenchLeader1,050,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–94.3%
SimpleBenchSimpleBench–73.1%†
Arena Hard PromptsArena (LMArena)–1484
LiveBench 2.0 ReasoningLiveBench90.6%–
LiveBench 1.0 ReasoningLiveBench–88.7%
Humanity's Last Exam (AA)Artificial Analysis–47.9%
HLE-Diamond (AA)Artificial Analysis64.0%45.2%
Kagi LLM BenchmarkKagi LLM Benchmark67.0%†–
ARC-AGI-1ARC Prize97.5%95.5%
ARC-AGI-2ARC Prize85.8%89.6%
ARC-AGI-3ARC Prize98.2%23.0%
CritPtArtificial Analysis–30.9%
CritPt v2 hard subset (AA)Artificial Analysis62.5%66.5%
MysteryMechanismVals AI36.9%30.2%
HLE-Diamond (Scale)Scale AI SEAL56.5%†33.8%†
Arena ExpertArena (LMArena)–1497
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%
ForecastBenchForecastBench–66.3%†
Coding
SciCodeSciCode–57.6%
FrontierCodeCognition–49.3%
Arena CodingArena (LMArena)–1520
Arena WebDevArena (LMArena)17571674
Show all 141 benchmarks
MetricPublisherGPT-6.2 Sol (max)GPT-6 Sol (max)
Coding
LiveBench 2.0 CodingLiveBench83.7%–
LiveBench 1.0 CodingLiveBench–81.8%
IOIVals AI–82.6%
Code MigrationVals AI–57.2%
ProgramBenchVals AI–2.0%
Vibe Code Bench v1.1Vals AI87.6%87.8%
Vibe Code Bench 1-100 v1.1Vals AI40.9%–
SWE Atlas v1.1Scale AI SEAL60.5%†–
SWE Atlas v1.1: Codebase QnAScale AI SEAL61.3%†–
SWE Atlas v1.1: Test WritingScale AI SEAL64.4%†–
SWE Atlas v1.1: RefactoringScale AI SEAL55.7%†–
MirrorCodeEpoch AI Benchmarking Hub–48.9%
ALE-BenchEpoch AI Benchmarking Hub–2462
WeirdML v3WeirdML–19.7%†
Terminal-Bench 4.0 (AA)Artificial Analysis60.1%43.9%
GameBench 2 OverallDuelLab GameBench 2–73.0†
GameBench 2 by reasoning settingDuelLab GameBench 2–79.2†
Design Arena WebsiteDesign Arena–1288†
FrontierCode 2.0 (AA)Artificial Analysis44.4%35.6%
Agents & tools
Terminal-BenchTerminal-Bench61.5%50.3%
APEX-AgentsMercor–54.3%
Arena AgentArena (LMArena)11.36.5
LiveBench Long AgenticLiveBench63.6%–
LiveBench BrowserLiveBench88.2%–
LiveBench Agentic CodingLiveBench–52.9%
Terminal-Bench 2.1 (Vals)Vals AI–83.2%
GDPval-AA v2.1Artificial Analysis–1514
ITBench SRE (AA)Artificial Analysis–49.4%
Analyst Agent (AA)Artificial Analysis53.8%–
CyberBenchVals AI–78.0%
Finance Agent v2Vals AI–49.0%
Finance Agent v2.1Vals AI58.9%–
Harvey's Legal Agent Benchmark v1.1Vals AI12.1%–
Harvey's Legal Agent Benchmark v1Vals AI–1.7%
Legal Research BenchVals AI37.0%28.9%
SREBenchVals AI–30.5%
Tax Agent BenchVals AI24.8%15.0%
Terminal-Bench 4.0 (Vals)Vals AI60.6%44.4%
Terminal-Bench ScienceVals AI58.6%30.0%
Arena SearchArena (LMArena)–1229
Arena Agent Task CompletionArena (LMArena)10.93.9
Vending-Bench 2Andon Labs–14427.9†
SpireClimbEpoch AI Benchmarking Hub–9.2%
AutomationBenchArtificial Analysis71.3%61.6%
GDP.pdf (AA)Artificial Analysis30.0%25.2%
Harvey LAB-AA v1.1Harvey11.1%3.6%
EnterpriseOps-GymArtificial Analysis28.9%–
AA-Briefcase v1.1Artificial Analysis16121476
Design Arena AgenticDesign Arena–1207†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis67.6%30.0%
CWE-Bench (AA)Artificial Analysis61.7%64.2%
DeepSec-Bench (AA)Artificial Analysis51.6%46.3%
CyberGym end-to-end (AA)Artificial Analysis0.0%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 MathematicsLiveBench–96.4%
Autoform-HardVals AI85.7%–
Arena MathsArena (LMArena)–1444
FrontierMath ErdősEpoch AI Benchmarking Hub–1.5%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–60.7%
LiveBench 2.0 Data AnalysisLiveBench81.1%–
LiveBench ResearchLiveBench90.1%–
LiveBench 1.0 Data AnalysisLiveBench–81.2%
AA-Omniscience v1.1Artificial Analysis40.421.4
PRBench LegalScale AI SEAL43.3%†38.6%†
BioMysteryBenchVals AI77.8%74.8%
Excel Modeling BenchmarkVals AI–71.5%
Excel Modeling Benchmark v1.1Vals AI74.3%–
MedCodeVals AI–47.1%
MedScribeVals AI–82.0%
Public Benefits Bench v1.1Vals AI–56.6%
Financial Coaching BenchVals AI–62.6%
DrugDiscoveryBenchScale AI SEAL62.2%†–
EBR-benchEpoch AI Benchmarking Hub–53.3%
AA-Omniscience v1.1: accuracyArtificial Analysis61.6%51.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis44.6%39.1%
HealthBench Professional (AA)OpenAI–62.3%
FACTS ParametricGoogle–76.1%†
Instruction following
LiveBench LanguageLiveBench–85.3%
LiveBench Instruction FollowingLiveBench–68.6%
MultiChallengeScale AI SEAL72.0%†–
Arena Instruction FollowingArena (LMArena)–1448
Human preference
Arena TextArena (LMArena)–1458
EQ-Bench Creative Writing v3EQ-Bench–2126†
Arena Creative WritingArena (LMArena)–1427
Arena Multi-turnArena (LMArena)–1468
Arena Longer QueriesArena (LMArena)–1466
Multimodal
Arena VisionArena (LMArena)–1233
LiveBench DesignLiveBench80.0%–
MMMU-ProArtificial Analysis–83.0%
Humanity's Sixth SenseScale AI SEAL56.8%†31.2%
Blueprint-Bench 2Epoch AI Benchmarking Hub–36.9%†
Furniture AssemblyEpoch AI Benchmarking Hub–58.3%
VIALS-AAHandshake AI62.7%–
AA-3DArtificial Analysis12591131
FACTS MultimodalGoogle–43.9%†
Long context
AA-LCR v1.1Artificial Analysis–83.7%
MLCRArtificial Analysis37.2%33.9%
FACTS GroundingGoogle–83.3%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–163.8†
LiveBench 2.0LiveBench80.3%–
LiveBench 1.0LiveBench–79.3%
AA Intelligence Index v5.0.1Artificial Analysis57.344.2
AA Intelligence Index v4.3.2Artificial Analysis–47.6
AA Progress Index v1Artificial Analysis–334
Vals IndexVals AI66.1–
Vals Finance IndexVals AI56.7%–
Vals RSI IndexVals AI–28.1%
Vals Science IndexVals AI57.8%45.0%
Vals Legal IndexVals AI66.7%–
AA Cyber IndexArtificial Analysis37.836.8
Safety & honesty
FORTRESSScale AI SEAL–13.5%†
DistressBenchScale AI SEAL–68.0%†

Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-6.2 Sol (max): BenchLeader Index 63.2 → 64.6.
  • GPT-6.2 Sol (max): 4 new results (VIALS-AA, Arena WebDev, Arena Agent…).
  • GPT-6.2 Sol (max): BenchLeader Index 62.4 → 63.2.
  • GPT-6.2 Sol (max): 2 new results (Vibe Code Bench 1-100 v1.1, Terminal-Bench).
  • GPT-6 Sol (max): BenchLeader Index 62.9 → 62.1.
  • GPT-6 Sol (max): 2 score revisions.
  • 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.

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

GPT-6.2 Sol vs GPT-6 Sol: questions

Is GPT-6.2 Sol better than GPT-6 Sol?
GPT-6.2 Sol (max) and GPT-6 Sol (max) are neck and neck on quality (64.6 vs 62.4, within the ±3.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 19 Nov 2026, so check the category scores for your use.
GPT-6.2 Sol vs GPT-6 Sol: which is cheaper, and will that change?
They cost the same: $4.00 per million tokens blended. No price change has been announced for either.
Is GPT-6.2 Sol or GPT-6 Sol better for coding?
GPT-6.2 Sol scores higher in coding (75 vs 66 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1757 for GPT-6.2 Sol against 1674 for GPT-6 Sol.
Which is faster, GPT-6.2 Sol or GPT-6 Sol?
GPT-6 Sol streams faster (115 vs 74 output tokens per second, Artificial Analysis 7-day median).
Is GPT-6.2 Sol or GPT-6 Sol better for agents and tool use?
GPT-6.2 Sol scores higher in agentic tasks (65 vs 60 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 61.5% for GPT-6.2 Sol against 50.3% for GPT-6 Sol.
More questions (4)
Which is better for long documents?
Both accept 1,050,000 tokens of context.
Which has lower latency?
GPT-6 Sol answers first: 39.1 s against 78.8 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-6.2 Sol vs GPT-6 Sol?
Across the 33 benchmarks both have, GPT-6.2 Sol leads 28, GPT-6 Sol leads 4 and 1 is a tie. Every overall index that rates both puts GPT-6.2 Sol ahead.
When was GPT-6.2 Sol released?
GPT-6.2 Sol was released on 17 Nov 2026.