BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Gemini 3.1 Pro vs GPT-6 Sol

Full profiles: Gemini 3.1 Pro (Google) and GPT-6 Sol (OpenAI): every benchmark, price and rank.

Updated · Data from 15 sources

As of 9 Nov 2026, Gemini 3.1 Pro and GPT-6 Sol are neck and neck on quality (60.6 vs 62.9 on the BenchLeader Index, inside the ±5.2 margin), and they cost about the same at $4.50 vs $4.00 per 1M tokens blended. Choose Gemini 3.1 Pro for multimodal (65 vs 61) and fast first answers (16.0 s vs 72.1 s); choose GPT-6 Sol for coding (67 vs 57), maths (69 vs 61), and human preference (64 vs 58).

Key facts (as of 9 Nov 2026)

  • Gemini 3.1 Pro scores 60.6 on the BenchLeader Index and GPT-6 Sol scores 62.9 (BenchLeader, 9 Nov 2026).
  • Gemini 3.1 Pro costs $4.50 per 1M tokens blended (list price, 9 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 37 benchmarks both models have, GPT-6 Sol leads 26 (BenchLeader, 9 Nov 2026).
  • On Arena WebDev, Gemini 3.1 Pro is rated 1446 and GPT-6 Sol 1674 (LMArena, as published by 9 Nov 2026).
Gemini 3.1 Pro benchmarks Google GPT-6 Sol benchmarks max OpenAIAdd a third model

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 Sol67 vs 57 category score; Arena WebDev 1674 vs 1446High
Agents & tool useGPT-6 Sol60 vs 57 category score; APEX-Agents 54.3% vs 35.1%Medium
MathsGPT-6 Sol69 vs 61 category score; FrontierMath Tiers 1–3 89.8% vs 59.6%High
ReasoningEither66 vs 66 category score; GPQA Diamond 94.1% vs 94.3%Either
KnowledgeGPT-6 Sol62 vs 56 category score; EBR-bench 53.3% vs 14.3%Medium
Long documentsEither66 vs 67 category score; AA-LCR v1.1 82.0% vs 83.7%Either
Images and other mediaGemini 3.1 Pro65 vs 61 category score; Arena Vision 1296 vs 1232Medium
Chat quality (human preference)GPT-6 Sol64 vs 58 on Arena votesMedium
Lowest costEither$4.50 vs $4.00 per 1M blended; agentic coding session $0.168 vs $0.160–
Fastest first answerGemini 3.1 Pro16.0 s (Gemini 3.1 Pro) vs 72.1 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

  • Gemini 3.1 Pro and GPT-6 Sol (max) are neck and neck on quality (60.6 vs 62.9, within the ±5.2 margin).
  • Gemini 3.1 Pro is stronger in instruction following, multimodal.
  • GPT-6 Sol (max) is stronger in agents & tools, coding, human preference, knowledge, long context, maths, reasoning.
  • They cost about the same ($4.00 per 1M blended).

At a glance

SpecGemini 3.1 ProGPT-6 Sol
DeveloperGoogleOpenAI
Released19 Feb 202622 Sep 2026
Context window (tokens)1,048,5761,050,000
Compared atGemini 3.1 ProGPT-6 Sol (max)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $12.00 / $0.200$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.

CategoryGemini 3.1 ProGPT-6 Sol (max)Leader
Reasoning65.966.2level
Coding56.766.5GPT-6 Sol
Agents & tools57.259.6GPT-6 Sol
Maths60.868.5GPT-6 Sol
Knowledge56.261.5GPT-6 Sol
Instruction following67.1–not comparable
Human preference58.464.2GPT-6 Sol
Multimodal64.560.7Gemini 3.1 Pro
Long context65.766.6level

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 contextMultimodalHumanpreferenceGemini 3.1 Pro, Reasoning: 65.9Gemini 3.1 Pro, Coding: 56.7Gemini 3.1 Pro, Agents & tools: 57.2Gemini 3.1 Pro, Maths: 60.8Gemini 3.1 Pro, Knowledge: 56.2Gemini 3.1 Pro, Long context: 65.7Gemini 3.1 Pro, Multimodal: 64.5Gemini 3.1 Pro, Human preference: 58.4GPT-6 Sol, Reasoning: 66.2GPT-6 Sol, Coding: 66.5GPT-6 Sol, Agents & tools: 59.6GPT-6 Sol, Maths: 68.5GPT-6 Sol, Knowledge: 61.5GPT-6 Sol, Long context: 66.6GPT-6 Sol, Multimodal: 60.7GPT-6 Sol, Human preference: 64.2

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

ModelIndex

Where sources disagree

Across the 37 benchmarks both have, Gemini 3.1 Pro leads 11, GPT-6 Sol leads 26. Every overall index that rates both puts Gemini 3.1 Pro ahead.

Overall indexGemini 3.1 ProGPT-6 Sol (max)Leader
BenchLeader Index60.662.9neck and neck
Arena Text14871457Gemini 3.1 Pro

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.

MeasureGemini 3.1 ProGPT-6 Sol (max)
Blended price per 1M tokens$4.50$4.00
Input / output per 1M$2.00 / $12.00$2.00 / $10.00
Cached input per 1M$0.200$0.200
Price per task: chat reply$0.0044$0.0038
Price per task: summarize a 30-page report$0.031$0.030
Price per task: code edit$0.030$0.027
Price per task: agentic coding session$0.168$0.160
Price per task: structured extraction$0.0064$0.0060
Agentic coding session, input mostly cached$0.087$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 speed110 tok/s121 tok/s
Time to first answer16.0 s72.1 s
Time to a complete answer35.5 s130.2 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.1 Pro scores 60.6 and takes 16 s to its first answer token; Gemini 3.1 Pro (high) scores 60.2 in 16 s. GPT-6 Sol (max) scores 62.9 and takes 72 s to its first answer token; GPT-6 Sol (xhigh) scores 58.6 in 24 s, GPT-6 Sol (high) scores 58.2 in 9 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

167 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.

MetricPublisherGemini 3.1 ProGPT-6 Sol (max)
BenchLeader IndexBenchLeader60.662.9
Agents & tools scoreBenchLeader57.259.6
Coding scoreBenchLeader56.766.5
Human preference scoreBenchLeader58.464.2
Instruction following scoreBenchLeader67.1–
Knowledge scoreBenchLeader56.261.5
Long context scoreBenchLeader65.766.6
Maths scoreBenchLeader60.868.5
Multimodal scoreBenchLeader64.560.7
Reasoning scoreBenchLeader65.966.2
Blended price $/MBenchLeader$4.50$4.00
Output speedBenchLeader110 tok/s121 tok/s
Time to first answerBenchLeader16.0 s72.1 s
Context windowBenchLeader1,048,576 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.1%94.3%
Humanity's Last ExamScale AI / CAIS46.4%–
SimpleBenchSimpleBench79.6%–
Arena Hard PromptsArena (LMArena)15081483
LiveBench 1.0 ReasoningLiveBench84.0%†88.7%
GPQA Diamond (AA)Artificial Analysis94.1%–
Humanity's Last Exam (AA)Artificial Analysis47.0%47.9%
HLE-Diamond (AA)Artificial Analysis31.4%45.2%
GPQA Diamond (Vals)Vals AI95.5%†–
EnigmaEvalScale AI SEAL36.8%†–
ARC-AGI-1ARC Prize98.0%95.5%
ARC-AGI-2ARC Prize77.1%89.6%
ARC-AGI-3ARC Prize0.4%23.0%
CritPtArtificial Analysis17.7%30.9%
CritPt v2 hard subset (AA)Artificial Analysis–66.5%
MysteryMechanismVals AI20.7%†30.2%
Chess PuzzlesEpoch AI Benchmarking Hub51.0%†56.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub34.0%†56.0%
CL-benchEpoch AI Benchmarking Hub20.8%–
CL-bench LifeEpoch AI Benchmarking Hub16.9%–
LMCAEpoch AI Benchmarking Hub53.8%†59.1%
DTBenchEpoch AI Benchmarking Hub95.5%†97.3%
ForecastBenchForecastBench64.3%–
Coding
SciCodeSciCode58.7%57.6%
WeirdMLWeirdML72.1%–
Show all 167 benchmarks
MetricPublisherGemini 3.1 ProGPT-6 Sol (max)
Coding
FrontierCodeCognition–49.3%
GSO-BenchGSO-Bench22.6%–
Arena CodingArena (LMArena)15201520
Arena WebDevArena (LMArena)14461674
LiveBench 1.0 CodingLiveBench76.5%†81.8%
LiveCodeBenchVals AI88.5%†–
IOIVals AI51.8%†82.6%
SWE-bench (Vals)Vals AI78.8%†–
SWE-Bench ProScale AI SEAL46.1%†–
Code MigrationVals AI17.3%†57.2%
ProgramBenchVals AI0.0%†2.0%
Vibe Code Bench 1-100Vals AI6.7%†–
Vibe Code Bench v1.1Vals AI32.0%†87.8%
SWE-Bench Pro (private)Scale AI SEAL46.1%†–
SWE Atlas: Codebase QnAScale AI SEAL13.5%–
SWE Atlas: RefactoringScale AI SEAL33.8%–
SWE Atlas: Test WritingScale AI SEAL29.8%–
MirrorCodeEpoch AI Benchmarking Hub8.9%†–
DeepSWE v1.1Epoch AI Benchmarking Hub11.7%–
ALE-BenchEpoch AI Benchmarking Hub1160.62462
AlgoTuneAlgoTune2.0–
Terminal-Bench 4.0 (AA)Artificial Analysis4.0%43.9%
Terminal-Bench 2.1 (AA)Artificial Analysis73.8%–
GameBench 2 OverallDuelLab GameBench 2–72.9†
GameBench 2 by reasoning settingDuelLab GameBench 2–79.3†
Design Arena WebsiteDesign Arena12301285†
FrontierCode 2.0 (AA)Artificial Analysis–35.6%
Agents & tools
Terminal-BenchTerminal-Bench80.2%50.3%
APEX-AgentsMercor35.1%54.3%
Arena AgentArena (LMArena)-4.37
LiveBench Agentic CodingLiveBench44.1%†52.9%
Terminal-Bench HardArtificial Analysis53.8%–
τ²-Bench Telecom (AA)Artificial Analysis95.6%–
Terminal-Bench 2.1 (Vals)Vals AI70.8%†83.2%
MCP AtlasScale AI SEAL78.2%†–
HiL-BenchScale AI SEAL35.3%–
τ³-bench Bankingτ²-bench26.0%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis14.6%–
GDPval-AA v2.1Artificial Analysis799–
τ³-Banking (AA)Artificial Analysis21.4%–
ITBench SRE (AA)Artificial Analysis30.3%49.4%
Analyst Agent (AA)Artificial Analysis41.3%–
APEX-Agents (AA)Artificial Analysis32.0%–
CyberBenchVals AI–78.0%
Finance Agent v2Vals AI43.0%†49.0%
Harvey's Legal Agent Benchmark v1Vals AI0.0%†1.7%
Legal Research BenchVals AI20.7%†28.9%
SREBenchVals AI0.0%†30.5%
Tax Agent BenchVals AI9.3%†15.0%
Terminal-Bench 2.0 (Vals)Vals AI67.4%†–
Terminal-Bench 4.0 (Vals)Vals AI2.5%†44.4%
Terminal-Bench ScienceVals AI1.4%†30.0%
Arena SearchArena (LMArena)12091229
BALROGBALROG57.0%–
DeepResearch BenchDeepResearch Bench47.8%†–
PostTrainBenchEpoch AI Benchmarking Hub22.0%–
ExploitBenchEpoch AI Benchmarking Hub26.1%–
METR Time HorizonsMETR77.0%–
GBAEvalEpoch AI Benchmarking Hub0.8%–
Vending-Bench 2Andon Labs911.214427.9†
AutomationBenchArtificial Analysis35.4%61.6%
GDP.pdf (AA)Artificial Analysis17.8%25.2%
Harvey LAB-AA v1.1Harvey0.0%3.6%
EnterpriseOps-GymArtificial Analysis42.2%–
AA-Briefcase v1.1Artificial Analysis4571476
Design Arena AgenticDesign Arena10831212†
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%
BrowseCompOpenAI31.2%–
DeepSearchQAGoogle60.2%–
FACTS SearchGoogle90.2%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.6%89.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%90.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub95.6%100.0%
ProofBenchVals AI26.0%83.0%†
LiveBench MathematicsLiveBench91.0%†96.4%
AIME (Vals)Vals AI98.1%†–
AIME 2026MathArena98.3%–
HMMT February 2026MathArena94.7%–
USAMO 2026MathArena74.4%–
MathArena ApexMathArena60.9%–
Arena MathsArena (LMArena)14881440
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub73.5%†60.7%
LiveBench 1.0 Data AnalysisLiveBench78.5%†81.2%
AA-Omniscience v1.1Artificial Analysis–21.4
MMLU-ProVals AI91.0%†–
LegalBenchVals AI87.4%†–
CorpFinVals AI64.5%†–
TaxEvalVals AI72.9%†–
MedQAVals AI96.4%†–
PRBench FinanceScale AI SEAL41.9%–
PRBench LegalScale AI SEAL44.0%38.6%†
MultiNRCScale AI SEAL64.7%–
BioMysteryBenchVals AI60.0%†74.8%
CaseLaw v2Vals AI64.8%†–
Excel Modeling BenchmarkVals AI52.6%†71.5%
MedCodeVals AI59.1%†47.1%
MedScribeVals AI76.1%†82.0%
Public Benefits Bench v1.1Vals AI53.8%†56.6%
DrugDiscoveryBenchScale AI SEAL41.9%†–
EBR-benchEpoch AI Benchmarking Hub14.3%53.3%
GDP.pdfEpoch AI Benchmarking Hub17.0%26.4%
AA-Omniscience v1.1: accuracyArtificial Analysis–51.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–39.1%
Global-MMLU-Lite (AA)Artificial Analysis93.2%–
HealthBench Professional (AA)OpenAI–62.3%
Instruction following
LiveBench LanguageLiveBench85.4%†85.3%
LiveBench Instruction FollowingLiveBench79.1%†68.6%
IFBenchArtificial Analysis77.1%–
MultiChallengeScale AI SEAL71.4%–
TutorBenchScale AI SEAL53.0%–
Arena Instruction FollowingArena (LMArena)14801448
Human preference
Arena TextArena (LMArena)14871457
EQ-Bench 4EQ-Bench1132–
Arena Creative WritingArena (LMArena)14821430
Arena Multi-turnArena (LMArena)14951466
Arena Longer QueriesArena (LMArena)14991466
Multimodal
Arena VisionArena (LMArena)12961232
MMMU-ProArtificial Analysis82.4%83.0%
MMMU-Pro (official)MMMU80.5%†–
MMMU-Pro (Vals)Vals AI88.2%†–
MortgageTaxVals AI69.4%†–
SAGEVals AI83.2%†–
VTBScale AI SEAL29.0%–
Blueprint-Bench 2Epoch AI Benchmarking Hub26.5%36.9%†
AA-3DArtificial Analysis–1131
Long context
AA-LCR v1.1Artificial Analysis82.0%83.7%
Arena DocumentArena (LMArena)1459–
MLCRArtificial Analysis11.1%33.9%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.2164.1†
LiveBench 1.0LiveBench77.0%†79.3%
AA Intelligence Index v5.0Artificial Analysis–44.2
AA Intelligence Index v4.3.2Artificial Analysis29.747.6
AA Progress Index v1Artificial Analysis296.1334
Vals RSI IndexVals AI–28.1%
Vals Science IndexVals AI27.4%†45.0%
Vals Multimodal IndexVals AI56.1%†–
AA Cyber IndexArtificial Analysis–36.8
Safety & honesty
FORTRESSScale AI SEAL29.8%13.5%†
MASKScale AI SEAL42.4%–

Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), 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): BenchLeader Index 63.5 → 62.9.
  • GPT-6 Sol (max): 2 score revisions.
  • Gemini 3.1 Pro: 1 new result (Arena Search).
  • GPT-6 Sol (max): 1 score revision.
  • Gemini 3.1 Pro: 1 score revision.
  • Gemini 3.1 Pro: 2 score revisions.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 6 new results (AA Intelligence Index v5.0, AA-Omniscience v1.1, CritPt v2 hard subset (AA)…).
  • 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

Gemini 3.1 Pro vs GPT-6 Sol: questions

Is Gemini 3.1 Pro better than GPT-6 Sol?
Gemini 3.1 Pro and GPT-6 Sol (max) are neck and neck on quality (60.6 vs 62.9, within the ±5.2 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
Gemini 3.1 Pro vs GPT-6 Sol: which is cheaper, and will that change?
GPT-6 Sol 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 Gemini 3.1 Pro or GPT-6 Sol better for coding?
GPT-6 Sol scores higher in coding (67 vs 57 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1446 for Gemini 3.1 Pro against 1674 for GPT-6 Sol.
Which is faster, Gemini 3.1 Pro or GPT-6 Sol?
GPT-6 Sol streams faster (121 vs 110 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.1 Pro or GPT-6 Sol better for agents and tool use?
GPT-6 Sol scores higher in agentic tasks (60 vs 57 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 80.2% for Gemini 3.1 Pro against 50.3% for GPT-6 Sol.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (66 vs 67). Both take about 1.1M tokens: Gemini 3.1 Pro 1,048,576, GPT-6 Sol 1,050,000.
Which has lower latency?
Gemini 3.1 Pro answers first: 16.0 s against 72.1 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 Gemini 3.1 Pro vs GPT-6 Sol?
Across the 37 benchmarks both have, Gemini 3.1 Pro leads 11, GPT-6 Sol leads 26. Every overall index that rates both puts Gemini 3.1 Pro ahead.
When was GPT-6 Sol released?
GPT-6 Sol was released on 22 Sep 2026.