BenchLeader

GPT-6 Sol vs Qwen3.7 Max

Full profiles: GPT-6 Sol (OpenAI) and Qwen3.7 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 14 sources

As of 19 Nov 2026, GPT-6 Sol and Qwen3.7 Max are neck and neck on quality (62.4 vs 59.8 on the BenchLeader Index, inside the ±4.8 margin), and they cost about the same at $4.00 vs $3.75 per 1M tokens blended. Choose GPT-6 Sol for agents & tools (60 vs 49), maths (68 vs 58), and human preference (64 vs 56); choose Qwen3.7 Max for fast first answers (14.1 s vs 39.1 s) and knowledge (61 vs 60), where it also streams faster.

Key facts (as of 19 Nov 2026)

  • GPT-6 Sol scores 62.4 on the BenchLeader Index and Qwen3.7 Max scores 59.8 (BenchLeader, 19 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 19 Nov 2026).
  • Qwen3.7 Max costs $3.75 per 1M tokens blended (list price, 19 Nov 2026).
  • Qwen3.7 Max streams faster than GPT-6 Sol (Artificial Analysis, 7-day median, 19 Nov 2026).
  • Of the 52 benchmarks both models have, GPT-6 Sol leads 41 (BenchLeader, 19 Nov 2026).
  • On Arena WebDev, GPT-6 Sol is rated 1674 and Qwen3.7 Max 1516 (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 Sol66 vs 59 category score; Arena WebDev 1674 vs 1516Medium
Agents & tool useGPT-6 Sol60 vs 49 category score; Arena Agent 6.5 vs -8.3High
MathsGPT-6 Sol68 vs 58 category score; FrontierMath Tiers 1–3 89.8% vs 64.6%High
ReasoningEither65 vs 64 category score; GPQA Diamond 94.3% vs 90.9%Either
KnowledgeQwen3.7 Max61 vs 60 category score; SimpleQA Verified 55.8% vs 60.7%Medium
Long documentsGPT-6 Sol67 vs 64 category score; AA-LCR v1.1 83.7% vs 79.0%Medium
Chat quality (human preference)GPT-6 Sol64 vs 56 on Arena votesHigh
Lowest costEither$4.00 vs $3.75 per 1M blended; agentic coding session $0.160 vs $0.180–
Fastest first answerQwen3.7 Max14.1 s (Qwen3.7 Max) vs 39.1 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

  • GPT-6 Sol (max) and Qwen3.7 Max are neck and neck on quality (62.4 vs 59.8, within the ±4.8 margin).
  • GPT-6 Sol (max) is stronger in agents & tools, coding, human preference, long context, maths, reasoning.
  • Qwen3.7 Max is stronger in knowledge.
  • They cost about the same ($3.75 per 1M blended).

At a glance

SpecGPT-6 SolQwen3.7 Max
DeveloperOpenAIAlibaba
Released22 Sep 202619 May 2026
Context window (tokens)1,050,0001,000,000
Compared atGPT-6 Sol (max)Qwen3.7 Max
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.200$2.50 / $7.50 / $0.500

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 Sol (max)Qwen3.7 MaxLeader
Reasoning64.964.2level
Coding65.558.6GPT-6 Sol
Agents & tools60.348.6GPT-6 Sol
Maths67.857.5GPT-6 Sol
Knowledge59.960.9Qwen3.7 Max
Instruction following–78.1not comparable
Human preference64.255.6GPT-6 Sol
Multimodal60.5–not comparable
Long context66.664.1GPT-6 Sol

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 contextHumanpreferenceGPT-6 Sol, Reasoning: 64.9GPT-6 Sol, Coding: 65.5GPT-6 Sol, Agents & tools: 60.3GPT-6 Sol, Maths: 67.8GPT-6 Sol, Knowledge: 59.9GPT-6 Sol, Long context: 66.6GPT-6 Sol, Human preference: 64.2Qwen3.7 Max, Reasoning: 64.2Qwen3.7 Max, Coding: 58.6Qwen3.7 Max, Agents & tools: 48.6Qwen3.7 Max, Maths: 57.5Qwen3.7 Max, Knowledge: 60.9Qwen3.7 Max, Long context: 64.1Qwen3.7 Max, Human preference: 55.6

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

Model, click to add or removeIndex

Where sources disagree

Across the 52 benchmarks both have, GPT-6 Sol leads 41, Qwen3.7 Max leads 10 and 1 is a tie. Every overall index that rates both puts Qwen3.7 Max ahead.

Overall indexGPT-6 Sol (max)Qwen3.7 MaxLeader
BenchLeader Index62.459.8neck and neck
Arena Text14581474Qwen3.7 Max

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 Sol (max)Qwen3.7 Max
Blended price per 1M tokens$4.00$3.75
Input / output per 1M$2.00 / $10.00$2.50 / $7.50
Cached input per 1M$0.200$0.500
Price per task: chat reply$0.0038$0.0033
Price per task: summarize a 30-page report$0.030$0.035
Price per task: code edit$0.027$0.026
Price per task: agentic coding session$0.160$0.180
Price per task: structured extraction$0.0060$0.0065
Agentic coding session, input mostly cached$0.079$0.090
Cost per benchmark task (AA Index)$2.47–
Output tokens per task (AA Index)54k–
Of which reasoning35k–
Time per task (AA Index)8 min–
Output speed115 tok/s145 tok/s
Time to first answer39.1 s14.1 s
Time to a complete answer, last measured 13 Nov 2026143.8 s31.2 s

Each model is compared at its best-ranked reasoning-effort setting. 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. Qwen3.7 Max scores 59.8 and takes 14 s to its first answer token. 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.

MetricPublisherGPT-6 Sol (max)Qwen3.7 Max
BenchLeader IndexBenchLeader62.459.8
Agents & tools scoreBenchLeader60.348.6
Coding scoreBenchLeader65.558.6
Human preference scoreBenchLeader64.255.6
Knowledge scoreBenchLeader59.960.9
Long context scoreBenchLeader66.664.1
Maths scoreBenchLeader67.857.5
Multimodal scoreBenchLeader60.5–
Reasoning scoreBenchLeader64.964.2
Instruction following scoreBenchLeader–78.1
Blended price $/MBenchLeader$4.00$3.75
Output speedBenchLeader115 tok/s145 tok/s
Time to first answerBenchLeader39.1 s14.1 s
Context windowBenchLeader1,050,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.3%90.9%
SimpleBenchSimpleBench73.1%†70.4%
Arena Hard PromptsArena (LMArena)14841494
LiveBench 1.0 ReasoningLiveBench88.7%83.3%
GPQA Diamond (AA)Artificial Analysis–92.3%
Humanity's Last Exam (AA)Artificial Analysis47.9%40.5%
HLE-Diamond (AA)Artificial Analysis45.2%–
GPQA Diamond (Vals)Vals AI–90.2%
ARC-AGI-1ARC Prize95.5%–
ARC-AGI-2ARC Prize89.6%–
ARC-AGI-3ARC Prize23.0%–
CritPtArtificial Analysis30.9%13.4%
CritPt v2 hard subset (AA)Artificial Analysis66.5%–
MysteryMechanismVals AI30.2%–
HLE-Diamond (Scale)Scale AI SEAL33.8%†–
Arena ExpertArena (LMArena)14971508
Chess PuzzlesEpoch AI Benchmarking Hub56.0%27.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub56.0%32.0%
LMCAEpoch AI Benchmarking Hub59.1%44.0%
DTBenchEpoch AI Benchmarking Hub97.3%92.3%
ForecastBenchForecastBench66.3%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–77.3%
SciCodeSciCode57.6%49.5%
FrontierCodeCognition49.3%–
Arena CodingArena (LMArena)15201524
Show all 136 benchmarks
MetricPublisherGPT-6 Sol (max)Qwen3.7 Max
Coding
Arena WebDevArena (LMArena)16741516
LiveBench 1.0 CodingLiveBench81.8%74.2%
LiveCodeBenchVals AI–87.1%
IOIVals AI82.6%–
SWE-bench (Vals)Vals AI–68.8%
Code MigrationVals AI57.2%13.1%
ProgramBenchVals AI2.0%–
Vibe Code Bench v1.1Vals AI87.8%47.7%
MirrorCodeEpoch AI Benchmarking Hub48.9%–
ALE-BenchEpoch AI Benchmarking Hub24621189.4
WeirdML v3WeirdML19.7%†–
Terminal-Bench 4.0 (AA)Artificial Analysis43.9%1.5%
Terminal-Bench 2.1 (AA)Artificial Analysis–74.5%
Startrise FrontendStartrise–63.6%
GameBench 2 OverallDuelLab GameBench 273.0†–
GameBench 2 by reasoning settingDuelLab GameBench 279.2†–
Design Arena WebsiteDesign Arena1288†–
FrontierCode 2.0 (AA)Artificial Analysis35.6%–
Agents & tools
Terminal-BenchTerminal-Bench50.3%–
APEX-AgentsMercor54.3%–
Arena AgentArena (LMArena)6.5-8.3
LiveBench Agentic CodingLiveBench52.9%43.6%
Terminal-Bench HardArtificial Analysis–50.8%
τ²-Bench Telecom (AA)Artificial Analysis–94.7%
Terminal-Bench 2.1 (Vals)Vals AI83.2%61.0%
GDPval-AA v2.1Artificial Analysis15141134
τ³-Banking (AA)Artificial Analysis–11.8%
ITBench SRE (AA)Artificial Analysis49.4%42.5%
Analyst Agent (AA)Artificial Analysis–18.8%
CyberBenchVals AI78.0%–
Finance Agent v2Vals AI49.0%47.8%
Harvey's Legal Agent Benchmark v1Vals AI1.7%1.7%
Legal Research BenchVals AI28.9%25.5%
SREBenchVals AI30.5%–
Tax Agent BenchVals AI15.0%15.8%
Terminal-Bench 2.0 (Vals)Vals AI–59.2%
Terminal-Bench 4.0 (Vals)Vals AI44.4%–
Terminal-Bench ScienceVals AI30.0%–
Arena SearchArena (LMArena)1229–
Arena Agent Task CompletionArena (LMArena)3.9-10.6
GBAEvalEpoch AI Benchmarking Hub–0.4%
Vending-Bench 2Andon Labs14427.9†–
SpireClimbEpoch AI Benchmarking Hub9.2%–
AutomationBenchArtificial Analysis61.6%23.0%
GDP.pdf (AA)Artificial Analysis25.2%8.6%
Harvey LAB-AA v1.1Harvey3.6%–
EnterpriseOps-GymArtificial Analysis–45.0%
AA-Briefcase v1.1Artificial Analysis1476917
Design Arena AgenticDesign Arena1207†1171
Terminal-Bench-Science 0.1 (AA)Artificial Analysis30.0%–
CWE-Bench (AA)Artificial Analysis64.2%–
DeepSec-Bench (AA)Artificial Analysis46.3%–
CyberGym end-to-end (AA)Artificial Analysis0.0%–
FACTS SearchGoogle92.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub89.8%64.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub90.0%34.1%
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%95.6%
ProofBenchVals AI83.0%†26.0%
LiveBench MathematicsLiveBench96.4%85.3%
Arena MathsArena (LMArena)14441481
FrontierMath ErdősEpoch AI Benchmarking Hub1.5%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub60.7%55.8%
LiveBench 1.0 Data AnalysisLiveBench81.2%71.8%
AA-Omniscience v1.1Artificial Analysis21.4–
MMLU-ProVals AI–89.3%
LegalBenchVals AI–84.9%
CorpFinVals AI–63.7%
TaxEvalVals AI–75.3%
PRBench LegalScale AI SEAL38.6%†–
BioMysteryBenchVals AI74.8%–
Excel Modeling BenchmarkVals AI71.5%57.0%
MedCodeVals AI47.1%38.8%
MedScribeVals AI82.0%79.4%
Public Benefits Bench v1.1Vals AI56.6%–
Financial Coaching BenchVals AI62.6%–
DrugDiscoveryBenchScale AI SEAL–29.3%†
EBR-benchEpoch AI Benchmarking Hub53.3%9.5%
AA-Omniscience v1.1: accuracyArtificial Analysis51.1%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis39.1%–
HealthBench Professional (AA)OpenAI62.3%–
FACTS ParametricGoogle76.1%†–
Instruction following
LiveBench LanguageLiveBench85.3%79.7%
LiveBench Instruction FollowingLiveBench68.6%74.0%
IFBenchArtificial Analysis–80.5%
Arena Instruction FollowingArena (LMArena)14481466
Human preference
Arena TextArena (LMArena)14581474
EQ-Bench 4EQ-Bench–1100
EQ-Bench Creative Writing v3EQ-Bench2126†–
Arena Creative WritingArena (LMArena)14271440
Arena Multi-turnArena (LMArena)14681481
Arena Longer QueriesArena (LMArena)14661491
Multimodal
Arena VisionArena (LMArena)1233–
MMMU-ProArtificial Analysis83.0%–
Humanity's Sixth SenseScale AI SEAL31.2%–
Blueprint-Bench 2Epoch AI Benchmarking Hub36.9%†–
Furniture AssemblyEpoch AI Benchmarking Hub58.3%–
AA-3DArtificial Analysis1131–
FACTS MultimodalGoogle43.9%†–
Long context
AA-LCR v1.1Artificial Analysis83.7%79.0%
MLCRArtificial Analysis33.9%14.4%
FACTS GroundingGoogle83.3%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub163.8†154.6
LiveBench 1.0LiveBench79.3%73.1%
AA Intelligence Index v5.0.1Artificial Analysis44.2–
AA Intelligence Index v4.3.2Artificial Analysis47.629.5
AA Progress Index v1Artificial Analysis334293.8
Vals RSI IndexVals AI28.1%–
Vals Science IndexVals AI45.0%–
AA Cyber IndexArtificial Analysis36.8–
Safety & honesty
FORTRESSScale AI SEAL13.5%†–
DistressBenchScale AI SEAL68.0%†–

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

  • Qwen3.7 Max: BenchLeader Index 60.3 → 59.8.
  • Qwen3.7 Max: 1 score revision.
  • 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.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.

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

GPT-6 Sol vs Qwen3.7 Max: questions

Is GPT-6 Sol better than Qwen3.7 Max?
GPT-6 Sol (max) and Qwen3.7 Max are neck and neck on quality (62.4 vs 59.8, within the ±4.8 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 Sol vs Qwen3.7 Max: which is cheaper, and will that change?
Qwen3.7 Max is cheaper today: $3.75 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-6 Sol or Qwen3.7 Max better for coding?
GPT-6 Sol scores higher in coding (66 vs 59 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1674 for GPT-6 Sol against 1516 for Qwen3.7 Max.
Which is faster, GPT-6 Sol or Qwen3.7 Max?
Qwen3.7 Max streams faster (145 vs 115 output tokens per second, Artificial Analysis 7-day median).
Is GPT-6 Sol or Qwen3.7 Max better for agents and tool use?
GPT-6 Sol scores higher in agentic tasks (60 vs 49 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 6.5 for GPT-6 Sol against -8.3 for Qwen3.7 Max.
More questions (4)
Which is better for long documents?
GPT-6 Sol scores higher on long-context benchmarks (67 vs 64). Both take about 1.1M tokens: GPT-6 Sol 1,050,000, Qwen3.7 Max 1,000,000.
Which has lower latency?
Qwen3.7 Max answers first: 14.1 s against 39.1 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 GPT-6 Sol vs Qwen3.7 Max?
Across the 52 benchmarks both have, GPT-6 Sol leads 41, Qwen3.7 Max leads 10 and 1 is a tie. Every overall index that rates both puts Qwen3.7 Max ahead.
When was GPT-6 Sol released?
GPT-6 Sol was released on 22 Sep 2026.