BenchLeader

GPT-5.4 vs Kimi K3.1 Pro

Full profiles: GPT-5.4 (OpenAI) and Kimi K3.1 Pro (Moonshot AI): every benchmark, price and rank.

Updated · Data from 14 sources

As of 10 Nov 2026, GPT-5.4 and Kimi K3.1 Pro are neck and neck on quality (63.2 vs 61.2 on the BenchLeader Index, inside the ±4.3 margin), and Kimi K3.1 Pro is 1.4× cheaper at $4.00 vs $5.63 per 1M tokens blended. Choose GPT-5.4 for reasoning (66 vs 60) and coding (65 vs 60), where it also streams ~2× faster; choose Kimi K3.1 Pro for maths (73 vs 65), multimodal (66 vs 61), and agents & tools (67 vs 63).

Key facts (as of 10 Nov 2026)

  • GPT-5.4 scores 63.2 on the BenchLeader Index and Kimi K3.1 Pro scores 61.2 (BenchLeader, 10 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 10 Nov 2026).
  • Kimi K3.1 Pro costs $4.00 per 1M tokens blended (list price, 10 Nov 2026).
  • GPT-5.4 streams ~2× faster than Kimi K3.1 Pro (Artificial Analysis, 7-day median, 10 Nov 2026).
  • Of the 7 benchmarks both models have, Kimi K3.1 Pro leads 7 (BenchLeader, 10 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-5.465 vs 60 category score; SciCode 56.6% vs 60.8%Medium
Agents & tool useKimi K3.1 Pro67 vs 63 category scoreMedium
MathsKimi K3.1 Pro73 vs 65 category score; ProofBench 91.0% vs 56.0%High
ReasoningGPT-5.466 vs 60 category score; Humanity's Last Exam (AA) 43.7% vs 52.5%Medium
KnowledgeKimi K3.1 Pro62 vs 59 category scoreMedium
Long documentsKimi K3.1 Pro68 vs 66 category score; AA-LCR v1.1 86.3% vs 82.0%Medium
Images and other mediaKimi K3.1 Pro66 vs 61 category score; MMMU-Pro 83.9% vs 78.4%Medium
Lowest costKimi K3.1 Pro$4.00 vs $5.63 per 1M blended; agentic coding session $0.160 vs $0.210–
Fastest first answerGPT-5.4111.7 s (GPT-5.4 (xhigh)) vs 161.8 s (Kimi K3.1 Pro) 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-5.4 (xhigh) and Kimi K3.1 Pro are neck and neck on quality (63.2 vs 61.2, within the ±4.3 margin).
  • GPT-5.4 (xhigh) is stronger in coding, instruction following, reasoning.
  • Kimi K3.1 Pro is stronger in agents & tools, knowledge, long context, maths, multimodal, composite.
  • Kimi K3.1 Pro is 1.4× cheaper ($4.00 vs $5.63 per 1M blended).
  • GPT-5.4 (xhigh) streams 2.4× faster (76 vs 32 tokens per second).

At a glance

SpecGPT-5.4Kimi K3.1 Pro
DeveloperOpenAIMoonshot AI
Released5 Mar 202623 Oct 2026
Context window (tokens)1,050,0001,048,576
Compared atGPT-5.4 (xhigh)Kimi K3.1 Pro
Open weightsNoYes
Price in / out / cached input per 1M$2.50 / $15.00 / $0.250$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-5.4 (xhigh)Kimi K3.1 ProLeader
Reasoning65.859.6GPT-5.4
Coding64.859.8GPT-5.4
Agents & tools63.067.1Kimi K3.1 Pro
Maths65.173.4Kimi K3.1 Pro
Knowledge58.661.5Kimi K3.1 Pro
Instruction following72.4–not comparable
Multimodal60.966.4Kimi K3.1 Pro
Long context65.768.0Kimi K3.1 Pro
Composite–54.8not 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 contextMultimodalGPT-5.4, Reasoning: 65.8GPT-5.4, Coding: 64.8GPT-5.4, Agents & tools: 63.0GPT-5.4, Maths: 65.1GPT-5.4, Knowledge: 58.6GPT-5.4, Long context: 65.7GPT-5.4, Multimodal: 60.9Kimi K3.1 Pro, Reasoning: 59.6Kimi K3.1 Pro, Coding: 59.8Kimi K3.1 Pro, Agents & tools: 67.1Kimi K3.1 Pro, Maths: 73.4Kimi K3.1 Pro, Knowledge: 61.5Kimi K3.1 Pro, Long context: 68.0Kimi K3.1 Pro, Multimodal: 66.4

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

ModelIndex

Where sources disagree

Across the 7 benchmarks both have, GPT-5.4 leads 0, Kimi K3.1 Pro leads 7. Every overall index that rates both puts Kimi K3.1 Pro ahead.

Overall indexGPT-5.4 (xhigh)Kimi K3.1 ProLeader
BenchLeader Index63.261.2neck and neck
Arena Text1475†1483Kimi K3.1 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.

MeasureGPT-5.4 (xhigh)Kimi K3.1 Pro
Blended price per 1M tokens$5.63$4.00
Input / output per 1M$2.50 / $15.00$2.00 / $10.00
Cached input per 1M$0.250$0.200
Price per task: chat reply$0.0055$0.0038
Price per task: summarize a 30-page report$0.039$0.030
Price per task: code edit$0.037$0.027
Price per task: agentic coding session$0.210$0.160
Price per task: structured extraction$0.0080$0.0060
Agentic coding session, input mostly cached$0.109$0.079
Cost per benchmark task (AA Index)–$3.68
Output tokens per task (AA Index)–72k
Of which reasoning–44k
Time per task (AA Index)–38 min
Output speed76 tok/s32 tok/s
Time to first answer111.7 s161.8 s
Time to a complete answer195.8 s397.6 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 (xhigh) scores 63.2 and takes 112 s to its first answer token; GPT-5.4 (low) scores 58.8 in 4 s, GPT-5.4 (high) scores 58.8 in 2 s. Kimi K3.1 Pro scores 61.2 and takes 162 s to its first answer token; Kimi K3.1 Pro (max) scores 60.4 in 162 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

162 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-5.4 (xhigh)Kimi K3.1 Pro
BenchLeader IndexBenchLeader63.261.2
Agents & tools scoreBenchLeader63.067.1
Coding scoreBenchLeader64.859.8
Instruction following scoreBenchLeader72.4–
Knowledge scoreBenchLeader58.661.5
Long context scoreBenchLeader65.768.0
Maths scoreBenchLeader65.173.4
Multimodal scoreBenchLeader60.966.4
Reasoning scoreBenchLeader65.859.6
Composite scoreBenchLeader–54.8
Blended price $/MBenchLeader$5.63$4.00
Output speedBenchLeader76 tok/s32 tok/s
Time to first answerBenchLeader111.7 s161.8 s
Context windowBenchLeader1,050,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.3%–
Humanity's Last ExamScale AI / CAIS36.2%–
Arena Hard PromptsArena (LMArena)1487†1501†
LiveBench 2.0 ReasoningLiveBench–91.1%
LiveBench 1.0 ReasoningLiveBench88.1%–
GPQA Diamond (AA)Artificial Analysis92.0%–
Humanity's Last Exam (AA)Artificial Analysis43.7%52.5%
HLE-Diamond (AA)Artificial Analysis–37.3%
GPQA Diamond (Vals)Vals AI91.7%–
Kagi LLM BenchmarkKagi LLM Benchmark63.8%†–
ARC-AGI-1ARC Prize93.7%–
ARC-AGI-2ARC Prize74.0%–
ARC-AGI-3ARC Prize0.2%†–
CritPtArtificial Analysis23.4%24.6%
CritPt v2 hard subset (AA)Artificial Analysis–49.5%
MysteryMechanismVals AI–26.1%†
Chess PuzzlesEpoch AI Benchmarking Hub48.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub37.0%–
CL-benchEpoch AI Benchmarking Hub27.9%–
CL-bench LifeEpoch AI Benchmarking Hub21.7%–
LMCAEpoch AI Benchmarking Hub52.0%57.6%†
DTBenchEpoch AI Benchmarking Hub94.4%93.3%†
ForecastBenchForecastBench63.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.9%†–
SciCodeSciCode56.6%60.8%
Show all 162 benchmarks
MetricPublisherGPT-5.4 (xhigh)Kimi K3.1 Pro
Coding
WeirdMLWeirdML77.7%–
GSO-BenchGSO-Bench31.4%–
Arena CodingArena (LMArena)1511†1526†
Arena WebDevArena (LMArena)1400†1688†
LiveBench 2.0 CodingLiveBench–67.8%
LiveBench 1.0 CodingLiveBench77.5%–
SciCode (AA)Artificial Analysis–60.8%
LiveCodeBenchVals AI84.1%–
IOIVals AI–81.9%†
SWE-bench (Vals)Vals AI78.2%–
SWE-Bench ProScale AI SEAL59.1%–
Code MigrationVals AI35.0%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI67.4%84.9%†
SWE-Bench Pro (private)Scale AI SEAL59.1%–
SWE Atlas: Codebase QnAScale AI SEAL40.8%–
SWE Atlas: RefactoringScale AI SEAL44.3%–
SWE Atlas: Test WritingScale AI SEAL44.4%–
MirrorCodeEpoch AI Benchmarking Hub15.6%†–
DeepSWE v1.1Epoch AI Benchmarking Hub51.8%–
ALE-BenchEpoch AI Benchmarking Hub1607†1932.8†
AlgoTuneAlgoTune1.9†–
Terminal-Bench 4.0 (AA)Artificial Analysis–67.2%
Terminal-Bench 2.1 (AA)Artificial Analysis78.3%–
Startrise FrontendStartrise–82.5%
GameBench 2 OverallDuelLab GameBench 253.4†78.2
GameBench 2 by reasoning settingDuelLab GameBench 261.884.0†
Design Arena WebsiteDesign Arena1194†1320
FrontierCode 1.1 (AA)Artificial Analysis–47.1%
FrontierCode 2.0 (AA)Artificial Analysis–25.4%
Agents & tools
Terminal-BenchTerminal-Bench81.8%†–
APEX-AgentsMercor52.4%†65.5%
Arena AgentArena (LMArena)–5.2†
LiveBench Long AgenticLiveBench–38.7%
LiveBench BrowserLiveBench–75.9%
LiveBench Agentic CodingLiveBench53.8%–
Terminal-Bench HardArtificial Analysis57.6%–
τ²-Bench Telecom (AA)Artificial Analysis87.1%–
MCP AtlasScale AI SEAL70.6%–
HiL-BenchScale AI SEAL9.7%†–
τ³-bench Bankingτ²-bench39.4%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–67.3%
GDPval-AA v2.1Artificial Analysis–1861
τ³-Banking (AA)Artificial Analysis39.6%–
Analyst Agent (AA)Artificial Analysis–38.8%
APEX-Agents (AA)Artificial Analysis33.3%–
Finance Agent v2.1Vals AI–61.5%†
Harvey's Legal Agent Benchmark v1.1Vals AI–11.7%†
Harvey's Legal Agent Benchmark v1Vals AI0.0%–
Legal Research BenchVals AI–37.5%†
SkillsBenchVals AI51.7%–
SREBenchVals AI–27.1%†
Tax Agent BenchVals AI–24.9%†
Terminal-Bench 2.0 (Vals)Vals AI58.4%†–
Terminal-Bench 4.0 (Vals)Vals AI–63.6%†
Terminal-Bench ScienceVals AI–31.4%†
Arena SearchArena (LMArena)1196†–
DeepResearch BenchDeepResearch Bench35.1%†–
PostTrainBenchEpoch AI Benchmarking Hub19.0%†–
METR Time HorizonsMETR74.3%–
GBAEvalEpoch AI Benchmarking Hub45.1%†–
Vending-Bench 2Andon Labs6144.2†–
AutomationBenchArtificial Analysis–73.3%
GDP.pdf (AA)Artificial Analysis–31.4%
AA-Briefcase v1.1Artificial Analysis–1674
Design Arena AgenticDesign Arena1035†1281
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–34.3%
CWE-Bench (AA)Artificial Analysis–60.8%
DeepSec-Bench (AA)Artificial Analysis–36.7%
CyberGym end-to-end (AA)Artificial Analysis–94.7%
DeepSearchQAGoogle63.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub78.6%–
FrontierMath Tier 4Epoch AI Benchmarking Hub49.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub95.3%–
ProofBenchVals AI56.0%91.0%
LiveBench MathematicsLiveBench94.2%–
AIME (Vals)Vals AI96.7%–
AIME 2026MathArena99.2%–
HMMT February 2026MathArena97.7%–
USAMO 2026MathArena95.2%–
MathArena ApexMathArena54.2%–
Arena MathsArena (LMArena)1459†–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub45.1%–
LiveBench 2.0 Data AnalysisLiveBench–79.1%
LiveBench ResearchLiveBench–82.1%
LiveBench 1.0 Data AnalysisLiveBench79.3%–
AA-Omniscience v1.1Artificial Analysis–29.9
MMLU-ProVals AI87.5%–
LegalBenchVals AI86.0%–
CorpFinVals AI65.3%–
TaxEvalVals AI74.0%–
MedQAVals AI96.1%–
PRBench FinanceScale AI SEAL45.6%†–
PRBench LegalScale AI SEAL44.4%†–
MultiNRCScale AI SEAL58.3%†–
BioMysteryBenchVals AI–75.6%†
CaseLaw v2Vals AI63.8%–
Excel Modeling Benchmark v1.1Vals AI–70.0%†
MedCodeVals AI41.3%–
MedScribeVals AI77.5%–
EBR-benchEpoch AI Benchmarking Hub25.4%–
AA-Omniscience v1.1: accuracyArtificial Analysis–48.9%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–62.7%
Instruction following
LiveBench LanguageLiveBench82.6%–
LiveBench Instruction FollowingLiveBench70.2%–
IFBenchArtificial Analysis74.0%–
Arena Instruction FollowingArena (LMArena)1460†1485†
Human preference
Arena TextArena (LMArena)1465†1483†
EQ-Bench 4EQ-Bench1258†–
Arena Creative WritingArena (LMArena)1433†1457†
Arena Multi-turnArena (LMArena)1480†1473†
Arena Longer QueriesArena (LMArena)1477†1488†
Multimodal
Arena VisionArena (LMArena)1292†–
LiveBench DesignLiveBench–73.7%
MMMU-ProArtificial Analysis78.4%83.9%
VISTAScale AI SEAL50.9%†–
MMMU-Pro (Vals)Vals AI87.5%–
MortgageTaxVals AI68.3%–
VTBScale AI SEAL29.2%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub27.1%†–
AA-3DArtificial Analysis–1112
Long context
AA-LCR v1.1Artificial Analysis82.0%86.3%
Arena DocumentArena (LMArena)1471†–
MLCRArtificial Analysis–38.3%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.8†162.0
LiveBench 2.0LiveBench–68.7%
LiveBench 1.0LiveBench78.0%–
AA Intelligence Index v5.0Artificial Analysis–46.5
AA Intelligence Index v4.3.2Artificial Analysis39.055.1
AA Progress Index v1Artificial Analysis311.6340.7
Vals IndexVals AI–62.5†
Vals Finance IndexVals AI–56.0%†
Vals RSI IndexVals AI15.5%–
Vals Science IndexVals AI–44.4%†
AA Cyber IndexArtificial Analysis–64.1
Safety & honesty
MASKScale AI SEAL89.7%†–
Metadata
AA Openness IndexArtificial Analysis–33.3

Data as of 2026-11-10. 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

  • Kimi K3.1 Pro: 2 new results (APEX-Agents, Epoch Capabilities Index).
  • Kimi K3.1 Pro: BenchLeader Index 61.8 → 61.2.
  • Kimi K3.1 Pro: 5 score revisions.
  • GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • Kimi K3.1 Pro: BenchLeader Index 61.3 → 61.8.
  • GPT-5.4 (xhigh): 1 score revision.
  • Kimi K3.1 Pro: 1 new result (GameBench 2 Overall); 1 score revision.
  • Kimi K3.1 Pro: 1 score revision.
  • Kimi K3.1 Pro: BenchLeader Index 59.3 → 61.3.
  • Kimi K3.1 Pro: 3 new results (SciCode, ProofBench, Startrise Frontend).

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

GPT-5.4 vs Kimi K3.1 Pro: questions

Is GPT-5.4 better than Kimi K3.1 Pro?
GPT-5.4 (xhigh) and Kimi K3.1 Pro are neck and neck on quality (63.2 vs 61.2, within the ±4.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 10 Nov 2026, so check the category scores for your use.
GPT-5.4 vs Kimi K3.1 Pro: which is cheaper, and will that change?
Kimi K3.1 Pro is cheaper today: $4.00 against $5.63 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.4 or Kimi K3.1 Pro better for coding?
GPT-5.4 scores higher in coding (65 vs 60 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 56.6% for GPT-5.4 against 60.8% for Kimi K3.1 Pro.
Which is faster, GPT-5.4 or Kimi K3.1 Pro?
GPT-5.4 streams ~2× faster (76 vs 32 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.4 or Kimi K3.1 Pro better for agents and tool use?
Kimi K3.1 Pro scores higher in agentic tasks (67 vs 63 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Kimi K3.1 Pro scores higher on long-context benchmarks (68 vs 66). Both take about 1.1M tokens: GPT-5.4 1,050,000, Kimi K3.1 Pro 1,048,576.
Which has lower latency?
GPT-5.4 answers first: 111.7 s against 161.8 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-5.4 vs Kimi K3.1 Pro?
Across the 7 benchmarks both have, GPT-5.4 leads 0, Kimi K3.1 Pro leads 7. Every overall index that rates both puts Kimi K3.1 Pro ahead.
When was Kimi K3.1 Pro released?
Kimi K3.1 Pro was released on 23 Oct 2026.