BenchLeader

GPT-6.1 Sol vs Grok 4

Full profiles: GPT-6.1 Sol (OpenAI) and Grok 4 (SpaceXAI): every benchmark, price and rank.

Updated · Data from 17 sources

As of 16 Nov 2026, GPT-6.1 Sol is ahead of Grok 4 on quality (66.6 vs 58.1 on the BenchLeader Index), and GPT-6.1 Sol is 1.5× cheaper at $4.00 vs $6.00 per 1M tokens blended. Choose GPT-6.1 Sol for knowledge (72 vs 56), coding (71 vs 56), and multimodal (66 vs 52); choose Grok 4 for fast first answers (17.5 s vs 166.7 s) and long context (68 vs 66), where it also streams faster.

Key facts (as of 16 Nov 2026)

  • GPT-6.1 Sol scores 66.6 on the BenchLeader Index and Grok 4 scores 58.1 (BenchLeader, 16 Nov 2026).
  • GPT-6.1 Sol costs $4.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Grok 4 costs $6.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Grok 4 streams faster than GPT-6.1 Sol (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 20 benchmarks both models have, GPT-6.1 Sol leads 20 (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-6.1 Sol71 vs 56 category score; Arena Coding 1540 vs 1435High
Agents & tool useGPT-6.1 Sol64 vs 59 category score; Terminal-Bench 60.9% vs 27.2%Medium
MathsGPT-6.1 Sol72 vs 58 category score; Arena Maths 1499 vs 1425High
ReasoningGPT-6.1 Sol71 vs 60 category score; GPQA Diamond 95.4% vs 87.0%High
KnowledgeGPT-6.1 Sol72 vs 56 category score; MedCode 48.8% vs 38.1%High
Long documentsGrok 468 vs 66 category score; AA-LCR v1.1 68.0% vs 83.0%Medium
Images and other mediaGPT-6.1 Sol66 vs 52 category score; Arena Vision 1286 vs 1210High
Chat quality (human preference)GPT-6.1 Sol67 vs 59 on Arena votesHigh
Lowest costGPT-6.1 Sol$4.00 vs $6.00 per 1M blended; agentic coding session $0.160 vs $0.240–
Fastest first answerGrok 417.5 s (Grok 4) vs 166.7 s (GPT-6.1 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-6.1 Sol (max) leads on quality: 66.6 vs 58.1.
  • GPT-6.1 Sol (max) is stronger in agents & tools, coding, human preference, knowledge, maths, multimodal, reasoning.
  • Grok 4 is stronger in long context.
  • GPT-6.1 Sol (max) is 1.5× cheaper ($4.00 vs $6.00 per 1M blended).
  • Grok 4 streams 1.4× faster (69 vs 50 tokens per second).

At a glance

SpecGPT-6.1 SolGrok 4
DeveloperOpenAISpaceXAI
Released29 Sep 20269 Jul 2025
Context window (tokens)1,050,000256,000
Compared atGPT-6.1 Sol (max)Grok 4
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.100$3.00 / $15.00 / –

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-6.1 Sol (max)Grok 4Leader
Reasoning71.460.0GPT-6.1 Sol
Coding71.155.9GPT-6.1 Sol
Agents & tools64.358.6GPT-6.1 Sol
Maths71.658.3GPT-6.1 Sol
Knowledge71.556.0GPT-6.1 Sol
Instruction following–62.5not comparable
Human preference67.158.5GPT-6.1 Sol
Multimodal65.652.0GPT-6.1 Sol
Long context66.268.3Grok 4
Composite67.9–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 & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceGPT-6.1 Sol, Reasoning: 71.4GPT-6.1 Sol, Coding: 71.1GPT-6.1 Sol, Agents & tools: 64.3GPT-6.1 Sol, Maths: 71.6GPT-6.1 Sol, Knowledge: 71.5GPT-6.1 Sol, Long context: 66.2GPT-6.1 Sol, Multimodal: 65.6GPT-6.1 Sol, Human preference: 67.1Grok 4, Reasoning: 60.0Grok 4, Coding: 55.9Grok 4, Agents & tools: 58.6Grok 4, Maths: 58.3Grok 4, Knowledge: 56.0Grok 4, Long context: 68.3Grok 4, Multimodal: 52.0Grok 4, Human preference: 58.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 20 benchmarks both have, GPT-6.1 Sol leads 20, Grok 4 leads 0. Every overall index that rates both puts GPT-6.1 Sol ahead.

Overall indexGPT-6.1 Sol (max)Grok 4Leader
BenchLeader Index66.658.1GPT-6.1 Sol
Arena Text14811411GPT-6.1 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-6.1 Sol (max)Grok 4
Blended price per 1M tokens$4.00$6.00
Input / output per 1M$2.00 / $10.00$3.00 / $15.00
Cached input per 1M$0.100–
Price per task: chat reply$0.0038$0.0057
Price per task: summarize a 30-page report$0.030$0.045
Price per task: code edit$0.027$0.041
Price per task: agentic coding session$0.160$0.240
Price per task: structured extraction$0.0060$0.0090
Agentic coding session, input mostly cached$0.074–
Cost per benchmark task (AA Index)$1.27–
Output tokens per task (AA Index)68k–
Of which reasoning49k–
Time per task (AA Index)23 min–
Output speed50 tok/s69 tok/s
Time to first answer166.7 s17.5 s
Time to a complete answer, last measured 13 Nov 2026429.6 s42.8 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Sol (max) scores 66.6 and takes 167 s to its first answer token; GPT-6.1 Sol (xhigh) scores 63.6 in 68 s, GPT-6.1 Sol (high) scores 63.4 in 33 s. Grok 4 scores 58.1 and takes 18 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

192 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-6.1 Sol (max)Grok 4
BenchLeader IndexBenchLeader66.658.1
Agents & tools scoreBenchLeader64.358.6
Coding scoreBenchLeader71.155.9
Composite scoreBenchLeader67.9–
Human preference scoreBenchLeader67.158.5
Knowledge scoreBenchLeader71.556.0
Long context scoreBenchLeader66.268.3
Maths scoreBenchLeader71.658.3
Multimodal scoreBenchLeader65.652.0
Reasoning scoreBenchLeader71.460.0
Instruction following scoreBenchLeader–62.5
Blended price $/MBenchLeader$4.00$6.00
Output speedBenchLeader50 tok/s69 tok/s
Time to first answerBenchLeader166.7 s17.5 s
Context windowBenchLeader1,050,000 tokens256,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub95.4%87.0%
SimpleBenchSimpleBench82.9%†60.5%
Arena Hard PromptsArena (LMArena)15051421
LiveBench 2.0 ReasoningLiveBench92.6%–
LiveBench 1.0 ReasoningLiveBench92.6%–
GPQA Diamond (AA)Artificial Analysis–87.7%
Humanity's Last Exam (AA)Artificial Analysis52.9%26.7%
HLE-Diamond (AA)Artificial Analysis58.8%–
GPQA Diamond (Vals)Vals AI–88.1%
Kagi LLM BenchmarkKagi LLM Benchmark–73.6%
GPQA Diamond (HELM)HELM Capabilities–72.6%
ARC-AGI-1ARC Prize96.5%66.7%†
ARC-AGI-2ARC Prize94.2%16.0%†
ARC-AGI-3ARC Prize96.2%–
CritPtArtificial Analysis31.7%2.0%
CritPt v2 hard subset (AA)Artificial Analysis69.5%–
MysteryMechanismVals AI46.4%–
Arena ExpertArena (LMArena)15251429
Chess PuzzlesEpoch AI Benchmarking Hub68.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub80.0%–
LMCAEpoch AI Benchmarking Hub62.8%–
DTBenchEpoch AI Benchmarking Hub96.5%–
ForecastBenchForecastBench–64.7%
Coding
SciCodeSciCode54.2%–
WeirdMLWeirdML–45.7%
Show all 192 benchmarks
MetricPublisherGPT-6.1 Sol (max)Grok 4
Coding
FrontierCodeCognition50.2%†–
Arena CodingArena (LMArena)15401435
Arena WebDevArena (LMArena)1743–
LiveBench 2.0 CodingLiveBench82.1%–
LiveBench 1.0 CodingLiveBench80.4%–
LiveCodeBenchVals AI–83.3%
IOIVals AI96.9%–
SWE-bench (Vals)Vals AI–57.8%
Aider PolyglotAider polyglot leaderboard–79.6%†
Code MigrationVals AI65.1%–
Code Migration v1.1Vals AI77.3%–
ProgramBenchVals AI3.0%–
SWE-bench MultimodalVals AI43.5%–
Vibe Code Bench v1.1Vals AI88.9%–
SWE Atlas v1.1Scale AI SEAL65.9%†–
SWE Atlas v1.1: Codebase QnAScale AI SEAL71.0%†–
SWE Atlas v1.1: Test WritingScale AI SEAL66.7%†–
SWE Atlas v1.1: RefactoringScale AI SEAL60.0%†–
SWE-Bench Pro V2Scale AI SEAL96.1%†–
MirrorCodeEpoch AI Benchmarking Hub61.1%–
ALE-BenchEpoch AI Benchmarking Hub2743.8–
WeirdML v3WeirdML38.3%†–
Terminal-Bench 4.0 (AA)Artificial Analysis56.1%–
Startrise FrontendStartrise78.6%†–
GameBench 2 OverallDuelLab GameBench 284.9†–
GameBench 2 by reasoning settingDuelLab GameBench 292.0†–
Design Arena WebsiteDesign Arena1315†1006
FrontierCode 1.1 (AA)Artificial Analysis49.1%–
FrontierCode 2.0 (AA)Artificial Analysis40.6%–
LiveCodeBench (AA)Artificial Analysis–81.9%
Agents & tools
Terminal-BenchTerminal-Bench60.9%27.2%
GDPvalOpenAI–21.1%†
CybenchCybench–43.0%
APEX-AgentsMercor60.0%–
Arena AgentArena (LMArena)12.5–
LiveBench Long AgenticLiveBench65.6%–
LiveBench BrowserLiveBench93.3%–
LiveBench Agentic CodingLiveBench54.5%–
Terminal-Bench HardArtificial Analysis–37.9%
τ²-Bench Telecom (AA)Artificial Analysis–74.8%
HiL-BenchScale AI SEAL62.3%†–
BFCL OverallBerkeley Function Calling Leaderboard–63.0%
GDPval-AA v2.1, normalised scoreArtificial Analysis54.8%–
GDPval-AA v2.1Artificial Analysis1607–
Analyst Agent (AA)Artificial Analysis50.0%–
CyberBenchVals AI39.3%–
Finance Agent v2Vals AI52.0%–
Finance Agent v2.1Vals AI61.8%–
Harvey's Legal Agent Benchmark v1.1Vals AI6.3%–
Harvey's Legal Agent Benchmark v1Vals AI5.4%–
Legal Research BenchVals AI38.5%–
Robo-benchVals AI28.3%–
SREBenchVals AI50.8%–
Tax Agent BenchVals AI21.8%–
Terminal-Bench 2.0 (Vals)Vals AI–28.1%
Terminal-Bench 4.0 (Vals)Vals AI55.0%–
Terminal-Bench ScienceVals AI52.9%–
Arena SearchArena (LMArena)12491123
Arena Agent Task CompletionArena (LMArena)11.7–
BALROGBALROG–43.6%
DeepResearch BenchDeepResearch Bench–47.3%
PostTrainBenchEpoch AI Benchmarking Hub38.8%–
METR Time HorizonsMETR–66.6%
Vending-Bench 2Andon Labs12860.6†–
SpireClimbEpoch AI Benchmarking Hub23.8%–
AutomationBenchArtificial Analysis64.9%–
GDP.pdf (AA)Artificial Analysis31.0%–
Harvey LAB-AA v1.1Harvey6.9%–
AA-Briefcase v1.1Artificial Analysis1555–
GDPxGDPx by SemiAnalysis8.4%–
Design Arena AgenticDesign Arena1375–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis58.1%–
MKA (AA)Artificial Analysis47.7%–
FACTS SearchGoogle92.8%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub93.7%–
FrontierMath Tier 4Epoch AI Benchmarking Hub100.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%84.0%
ProofBenchVals AI99.0%†–
LiveBench MathematicsLiveBench96.8%–
AIME (Vals)Vals AI–90.6%
MGSMVals AI–90.9%
IMO 2025MathArena–21.4%
MathArena ApexMathArena–2.1%
ArXivMathMathArena92.8%–
BrokenArXivMathArena83.1%–
Omni-MATH (HELM)HELM Capabilities–60.3%
MATH 500Vals AI–96.2%
Arena MathsArena (LMArena)14991425
FrontierMath ErdősEpoch AI Benchmarking Hub4.4%–
AIME 2025 (AA)Artificial Analysis–92.7%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub73.9%–
LiveBench 2.0 Data AnalysisLiveBench82.7%–
LiveBench ResearchLiveBench90.0%–
LiveBench 1.0 Data AnalysisLiveBench82.7%–
AA-Omniscience v1.1Artificial Analysis42.0–
MMLU-ProVals AI–85.3%
LegalBenchVals AI–83.2%
CorpFinVals AI–66.0%
TaxEvalVals AI–65.1%
MedQAVals AI–92.5%
PRBench FinanceScale AI SEAL46.2%†–
PRBench LegalScale AI SEAL47.9%†–
MMLU-Pro (HELM)HELM Capabilities–85.1%
BioMysteryBenchVals AI79.6%–
CaseLaw v2Vals AI–65.8%
ClaimBenchVals AI100.0%–
Excel Modeling BenchmarkVals AI70.8%–
Excel Modeling Benchmark v1.1Vals AI71.1%–
MedCodeVals AI48.8%38.1%
MedScribeVals AI86.5%78.2%
Public Benefits Bench v1.1Vals AI59.3%–
Access to Justice BenchmarkVals AI65.8%–
Financial Coaching BenchVals AI68.5%–
Immigration BenchVals AI67.8%–
EBR-benchEpoch AI Benchmarking Hub54.3%–
GDP.pdfEpoch AI Benchmarking Hub35.0%–
AA-Omniscience v1.1: accuracyArtificial Analysis61.8%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis48.1%–
Global-MMLU-Lite (AA)Artificial Analysis–89.5%
HealthBench Professional (AA)OpenAI65.1%–
FACTS ParametricGoogle83.8%†–
Instruction following
LiveBench LanguageLiveBench90.1%–
LiveBench Instruction FollowingLiveBench74.2%–
IFBenchArtificial Analysis–53.7%
MultiChallengeScale AI SEAL82.0%†–
IFEval (HELM)HELM Capabilities–94.9%
WildBench (HELM)HELM Capabilities–79.7%
Arena Instruction FollowingArena (LMArena)14821396
Human preference
Arena TextArena (LMArena)14811411
EQ-Bench 4EQ-Bench1272†–
Arena Creative WritingArena (LMArena)14491394
Arena Multi-turnArena (LMArena)14861413
Arena Longer QueriesArena (LMArena)14881416
Lech Mazur Creative WritingLech Mazur–76.9%
Multimodal
Arena VisionArena (LMArena)12861210
LiveBench DesignLiveBench79.6%–
MMMU-ProArtificial Analysis86.0%68.8%
MMMU-Pro (Vals)Vals AI–76.3%
MortgageTaxVals AI–44.5%
SAGEVals AI90.5%–
Humanity's Sixth SenseScale AI SEAL46.6%–
GeoBenchGeoBench–45.0%
Blueprint-Bench 2Epoch AI Benchmarking Hub43.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub80.0%–
VIALS-AAHandshake AI59.0%–
Code2Video-AAArtificial Analysis1369–
AA-3DArtificial Analysis1121–
FACTS MultimodalGoogle52.6%†–
Long context
Fiction.LiveBench 120kFiction.live–96.9%
AA-LCR v1.1Artificial Analysis83.0%68.0%
MLCRArtificial Analysis38.3%–
FACTS GroundingGoogle78.0%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.5†146.9
LiveBench 2.0LiveBench81.4%–
LiveBench 1.0LiveBench81.6%–
AA Intelligence Index v5.0.1Artificial Analysis54.6–
AA Intelligence Index v4.3.2Artificial Analysis51.822.5
AA Progress Index v1Artificial Analysis348.5262.3
Vals IndexVals AI63.9–
HELM Capabilities meanHELM Capabilities–78.5%
Vals Finance IndexVals AI55.8%–
Vals RSI IndexVals AI26.6%–
Vals Science IndexVals AI59.6%–
Vals Router IndexVals AI63.9%†–
Vals Legal IndexVals AI68.7%–
Safety & honesty
DistressBenchScale AI SEAL74.2%†–
Metadata
AA Openness IndexArtificial Analysis–5.6

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-6.1 Sol (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…); 1 score revision.
  • GPT-6.1 Sol (max): 1 score revision.
  • Grok 4: 1 new result (AIME 2025 (AA)).
  • GPT-6.1 Sol (max): 1 score revision.
  • GPT-6.1 Sol (max): 1 new result (PostTrainBench).
  • GPT-6.1 Sol (max): 1 new result (MirrorCode); 1 score revision.
  • GPT-6.1 Sol (max): BenchLeader Index 67.4 → 66.9.
  • GPT-6.1 Sol (max): 2 score revisions.
  • GPT-6.1 Sol (max): 3 score revisions.
  • Grok 4: 1 new result (Arena Search).

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

GPT-6.1 Sol vs Grok 4: questions

Is GPT-6.1 Sol better than Grok 4?
GPT-6.1 Sol (max) leads on quality: 66.6 vs 58.1. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
GPT-6.1 Sol vs Grok 4: which is cheaper, and will that change?
GPT-6.1 Sol is cheaper today: $4.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-6.1 Sol or Grok 4 better for coding?
GPT-6.1 Sol scores higher in coding (71 vs 56 on the category index, where 50 is average). On Arena Coding, the top shared coding benchmark, it is 1540 for GPT-6.1 Sol against 1435 for Grok 4.
Which is faster, GPT-6.1 Sol or Grok 4?
Grok 4 streams faster (69 vs 50 output tokens per second, Artificial Analysis 7-day median).
Is GPT-6.1 Sol or Grok 4 better for agents and tool use?
GPT-6.1 Sol scores higher in agentic tasks (64 vs 59 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 60.9% for GPT-6.1 Sol against 27.2% for Grok 4.
More questions (4)
Which is better for long documents?
Grok 4 scores higher on long-context benchmarks (68 vs 66). GPT-6.1 Sol accepts more context: 1,050,000 against 256,000 tokens for Grok 4.
Which has lower latency?
Grok 4 answers first: 17.5 s against 166.7 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-6.1 Sol vs Grok 4?
Across the 20 benchmarks both have, GPT-6.1 Sol leads 20, Grok 4 leads 0. Every overall index that rates both puts GPT-6.1 Sol ahead.
When was GPT-6.1 Sol released?
GPT-6.1 Sol was released on 29 Sep 2026.