BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

GPT-5.4 vs Kimi K3.1 Pro Together

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

Updated · Data from 12 sources

As of 9 Nov 2026, GPT-5.4 and Kimi K3.1 Pro Together are neck and neck on quality (63.2 vs 60.5 on the BenchLeader Index, inside the ±3.4 margin). Kimi K3.1 Pro Together leads in every category we measure both in.

Key facts (as of 9 Nov 2026)

  • GPT-5.4 scores 63.2 on the BenchLeader Index and Kimi K3.1 Pro Together scores 60.5 (BenchLeader, 9 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 7 benchmarks both models have, Kimi K3.1 Pro Together leads 5 (BenchLeader, 9 Nov 2026).
GPT-5.4 benchmarks xhigh OpenAI Kimi K3.1 Pro Together benchmarks max Moonshot AIAdd 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
MathsEither65 vs 66 category score; FrontierMath Tiers 1–3 78.6% vs 78.3%Either
ReasoningKimi K3.1 Pro Together67 vs 66 category score; GPQA Diamond 94.2% vs 93.3%Medium
KnowledgeKimi K3.1 Pro Together68 vs 59 category score; SimpleQA Verified 62.2% vs 45.1%High
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 Together (max) are neck and neck on quality (63.2 vs 60.5, within the ±3.4 margin).
  • GPT-5.4 (xhigh) is stronger in agents & tools, coding, instruction following, long context, multimodal.
  • Kimi K3.1 Pro Together (max) is stronger in knowledge, maths, reasoning.

At a glance

SpecGPT-5.4Kimi K3.1 Pro Together
DeveloperOpenAIMoonshot AI
Released5 Mar 202623 Oct 2026
Context window (tokens)1,050,000–
Compared atGPT-5.4 (xhigh)Kimi K3.1 Pro Together (max)
Open weightsNoNo
Price in / out / cached input per 1M$2.50 / $15.00 / $0.250–

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 Pro Together (max)Leader
Reasoning65.867.1Kimi K3.1 Pro Together
Coding64.8–not comparable
Agents & tools63.0–not comparable
Maths65.265.8level
Knowledge58.867.6Kimi K3.1 Pro Together
Instruction following72.4–not comparable
Multimodal60.9–not comparable
Long context65.7–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 avg75ReasoningMathsKnowledgeGPT-5.4, Reasoning: 65.8GPT-5.4, Maths: 65.2GPT-5.4, Knowledge: 58.8Kimi K3.1 Pro Together, Reasoning: 67.1Kimi K3.1 Pro Together, Maths: 65.8Kimi K3.1 Pro Together, Knowledge: 67.6

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

ModelIndex

Where sources disagree

Across the 7 benchmarks both have, GPT-5.4 leads 2, Kimi K3.1 Pro Together leads 5.

Overall indexGPT-5.4 (xhigh)Kimi K3.1 Pro Together (max)Leader
BenchLeader Index63.260.5neck and neck

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 Together (max)
Blended price per 1M tokens$5.63–
Input / output per 1M$2.50 / $15.00– / –
Cached input per 1M$0.250–
Price per task: chat reply$0.0055–
Price per task: summarize a 30-page report$0.039–
Price per task: code edit$0.037–
Price per task: agentic coding session$0.210–
Price per task: structured extraction$0.0080–
Agentic coding session, input mostly cached$0.109–
Output speed73 tok/s–
Time to first answer122.8 s–
Time to a complete answer204.9 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 (xhigh) scores 63.2 and takes 123 s to its first answer token; GPT-5.4 (low) scores 58.8 in 3 s, GPT-5.4 (high) scores 58.8 in 2 s. Kimi K3.1 Pro Together (max) scores 60.5. 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

114 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 Together (max)
BenchLeader IndexBenchLeader63.260.5
Agents & tools scoreBenchLeader63.0–
Coding scoreBenchLeader64.8–
Instruction following scoreBenchLeader72.4–
Knowledge scoreBenchLeader58.867.6
Long context scoreBenchLeader65.7–
Maths scoreBenchLeader65.265.8
Multimodal scoreBenchLeader60.9–
Reasoning scoreBenchLeader65.867.1
Blended price $/MBenchLeader$5.63–
Output speedBenchLeader73 tok/s–
Time to first answerBenchLeader122.8 s–
Context windowBenchLeader1,050,000 tokens–
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.3%94.2%
Humanity's Last ExamScale AI / CAIS36.2%–
Arena Hard PromptsArena (LMArena)1487†–
LiveBench 1.0 ReasoningLiveBench88.1%–
GPQA Diamond (AA)Artificial Analysis92.0%–
Humanity's Last Exam (AA)Artificial Analysis43.7%–
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%–
Chess PuzzlesEpoch AI Benchmarking Hub48.0%45.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub37.0%42.0%
CL-benchEpoch AI Benchmarking Hub27.9%–
CL-bench LifeEpoch AI Benchmarking Hub21.7%–
LMCAEpoch AI Benchmarking Hub52.0%–
DTBenchEpoch AI Benchmarking Hub94.4%–
ForecastBenchForecastBench63.1%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.9%†–
SciCodeSciCode56.6%–
WeirdMLWeirdML77.7%–
GSO-BenchGSO-Bench31.4%–
Arena CodingArena (LMArena)1511†–
Arena WebDevArena (LMArena)1400†–
Show all 114 benchmarks
MetricPublisherGPT-5.4 (xhigh)Kimi K3.1 Pro Together (max)
Coding
LiveBench 1.0 CodingLiveBench77.5%–
LiveCodeBenchVals AI84.1%–
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%–
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†–
AlgoTuneAlgoTune1.9†–
Terminal-Bench 2.1 (AA)Artificial Analysis78.3%–
GameBench 2 OverallDuelLab GameBench 253.4†–
GameBench 2 by reasoning settingDuelLab GameBench 261.8–
Design Arena WebsiteDesign Arena1195†–
Agents & tools
Terminal-BenchTerminal-Bench81.8%†–
APEX-AgentsMercor52.4%†–
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%–
τ³-Banking (AA)Artificial Analysis39.6%–
APEX-Agents (AA)Artificial Analysis33.3%–
Harvey's Legal Agent Benchmark v1Vals AI0.0%–
SkillsBenchVals AI51.7%–
Terminal-Bench 2.0 (Vals)Vals AI58.4%†–
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†–
Design Arena AgenticDesign Arena1038†–
DeepSearchQAGoogle63.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub78.6%78.3%
FrontierMath Tier 4Epoch AI Benchmarking Hub49.0%65.8%
OTIS Mock AIMEEpoch AI Benchmarking Hub95.3%100.0%
ProofBenchVals AI56.0%–
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%62.2%
LiveBench 1.0 Data AnalysisLiveBench79.3%–
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%†–
CaseLaw v2Vals AI63.8%–
MedCodeVals AI41.3%–
MedScribeVals AI77.5%–
EBR-benchEpoch AI Benchmarking Hub25.4%–
Instruction following
LiveBench LanguageLiveBench82.6%–
LiveBench Instruction FollowingLiveBench70.2%–
IFBenchArtificial Analysis74.0%–
Arena Instruction FollowingArena (LMArena)1460†–
Human preference
Arena TextArena (LMArena)1465†–
EQ-Bench 4EQ-Bench1258†–
Arena Creative WritingArena (LMArena)1433†–
Arena Multi-turnArena (LMArena)1480†–
Arena Longer QueriesArena (LMArena)1477†–
Multimodal
Arena VisionArena (LMArena)1292†–
MMMU-ProArtificial Analysis78.4%–
VISTAScale AI SEAL50.9%†–
MMMU-Pro (Vals)Vals AI87.5%–
MortgageTaxVals AI68.3%–
VTBScale AI SEAL29.2%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub27.1%†–
Long context
AA-LCR v1.1Artificial Analysis82.0%–
Arena DocumentArena (LMArena)1471†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.8†–
LiveBench 1.0LiveBench78.0%–
AA Intelligence Index v4.3.2Artificial Analysis39.0–
AA Progress Index v1Artificial Analysis311.6–
Vals RSI IndexVals AI15.5%–
Safety & honesty
MASKScale AI SEAL89.7%†–

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-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • Kimi K3.1 Pro Together (max): first results.
  • GPT-5.4 (xhigh): 1 score revision.
  • GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).
  • GPT-5.4 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).
  • GPT-5.4 (xhigh): 2 new results (USAMO 2026, τ³-bench Banking).
  • GPT-5.4 (xhigh): 1 score revision.
  • GPT-5.4 (xhigh): 1 new result (SWE Atlas: Codebase QnA).

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

GPT-5.4 vs Kimi K3.1 Pro Together: questions

Is GPT-5.4 better than Kimi K3.1 Pro Together?
GPT-5.4 (xhigh) and Kimi K3.1 Pro Together (max) are neck and neck on quality (63.2 vs 60.5, within the ±3.4 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.
Do independent benchmarks agree on GPT-5.4 vs Kimi K3.1 Pro Together?
Across the 7 benchmarks both have, GPT-5.4 leads 2, Kimi K3.1 Pro Together leads 5.
When was Kimi K3.1 Pro Together released?
Kimi K3.1 Pro Together was released on 23 Oct 2026.