BenchLeader

Gemini 3.1 Pro vs Kimi K3.1 Pro

Full profiles: Gemini 3.1 Pro (Google) and Kimi K3.1 Pro (Moonshot AI): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, Gemini 3.1 Pro and Kimi K3.1 Pro are neck and neck on quality (60.4 vs 61.8 on the BenchLeader Index, inside the ±4.5 margin), and they cost about the same at $4.50 vs $4.00 per 1M tokens blended. Choose Gemini 3.1 Pro for knowledge (66 vs 58) and reasoning (65 vs 59) and fast first answers (15.2 s vs 157.4 s), where it also streams 3×+ faster; choose Kimi K3.1 Pro for agents & tools (65 vs 57), maths (73 vs 66), and coding (60 vs 59).

Key facts (as of 16 Nov 2026)

  • Gemini 3.1 Pro scores 60.4 on the BenchLeader Index and Kimi K3.1 Pro scores 61.8 (BenchLeader, 16 Nov 2026).
  • Gemini 3.1 Pro costs $4.50 per 1M tokens blended (list price, 16 Nov 2026).
  • Kimi K3.1 Pro costs $4.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Gemini 3.1 Pro streams 3×+ faster than Kimi K3.1 Pro (Artificial Analysis, 7-day median, 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
CodingKimi K3.1 Pro60 vs 59 category scoreMedium
Agents & tool useKimi K3.1 Pro65 vs 57 category scoreHigh
MathsKimi K3.1 Pro73 vs 66 category scoreHigh
ReasoningGemini 3.1 Pro65 vs 59 category scoreMedium
KnowledgeGemini 3.1 Pro66 vs 58 category scoreMedium
Lowest costEither$4.50 vs $4.00 per 1M blended; agentic coding session $0.168 vs $0.160–
Fastest first answerGemini 3.1 Pro15.2 s (Gemini 3.1 Pro (high)) vs 157.4 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

  • Gemini 3.1 Pro (high) and Kimi K3.1 Pro are neck and neck on quality (60.4 vs 61.8, within the ±4.5 margin).
  • Gemini 3.1 Pro (high) is stronger in knowledge, reasoning.
  • Kimi K3.1 Pro is stronger in agents & tools, coding, maths.
  • They cost about the same ($4.00 per 1M blended).
  • Gemini 3.1 Pro (high) streams 3.7× faster (111 vs 30 tokens per second).

At a glance

SpecGemini 3.1 ProKimi K3.1 Pro
DeveloperGoogleMoonshot AI
Released19 Feb 202623 Oct 2026
Context window (tokens)1,048,5761,048,576
Compared atGemini 3.1 Pro (high)Kimi K3.1 Pro
Open weightsNoYes
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 Pro (high)Kimi K3.1 ProLeader
Reasoning64.759.2Gemini 3.1 Pro
Coding58.659.6Kimi K3.1 Pro
Agents & tools56.764.6Kimi K3.1 Pro
Maths65.773.4Kimi K3.1 Pro
Knowledge65.658.2Gemini 3.1 Pro
Multimodal–66.3not comparable
Long context–67.9not 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 & toolsMathsKnowledgeGemini 3.1 Pro, Reasoning: 64.7Gemini 3.1 Pro, Coding: 58.6Gemini 3.1 Pro, Agents & tools: 56.7Gemini 3.1 Pro, Maths: 65.7Gemini 3.1 Pro, Knowledge: 65.6Kimi K3.1 Pro, Reasoning: 59.2Kimi K3.1 Pro, Coding: 59.6Kimi K3.1 Pro, Agents & tools: 64.6Kimi K3.1 Pro, Maths: 73.4Kimi K3.1 Pro, Knowledge: 58.2

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

Model, click to add or removeIndex

Where sources disagree

Across the 0 benchmarks both have, Gemini 3.1 Pro leads 0, Kimi K3.1 Pro leads 0. Every overall index that rates both puts Gemini 3.1 Pro ahead.

Overall indexGemini 3.1 Pro (high)Kimi K3.1 ProLeader
BenchLeader Index60.461.8neck and neck
Arena Text1487†1485Gemini 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 Pro (high)Kimi K3.1 Pro
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)–$3.68
Output tokens per task (AA Index)–72k
Of which reasoning–44k
Time per task (AA Index)–40 min
Output speed111 tok/s30 tok/s
Time to first answer15.2 s157.4 s
Time to a complete answer, last measured 13 Nov 202637.5 s417.5 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.1 Pro (high) scores 60.4 and takes 15 s to its first answer token; Gemini 3.1 Pro scores 59.9 in 15 s. Kimi K3.1 Pro scores 61.8 and takes 157 s to its first answer token; Kimi K3.1 Pro (max) scores 59.9 in 157 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

199 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 Pro (high)Kimi K3.1 Pro
BenchLeader IndexBenchLeader60.461.8
Agents & tools scoreBenchLeader56.764.6
Coding scoreBenchLeader58.659.6
Knowledge scoreBenchLeader65.658.2
Maths scoreBenchLeader65.773.4
Reasoning scoreBenchLeader64.759.2
Long context scoreBenchLeader–67.9
Multimodal scoreBenchLeader–66.3
Blended price $/MBenchLeader$4.50$4.00
Output speedBenchLeader111 tok/s30 tok/s
Time to first answerBenchLeader15.2 s157.4 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.4%–
Humanity's Last ExamScale AI / CAIS46.4%†–
SimpleBenchSimpleBench79.6%†–
Arena Hard PromptsArena (LMArena)1508†1504†
LiveBench 2.0 ReasoningLiveBench–91.1%†
LiveBench 1.0 ReasoningLiveBench84.0%–
GPQA Diamond (AA)Artificial Analysis94.1%†–
Humanity's Last Exam (AA)Artificial Analysis47.0%†52.5%
HLE-Diamond (AA)Artificial Analysis31.4%†37.3%
GPQA Diamond (Vals)Vals AI95.5%–
EnigmaEvalScale AI SEAL36.8%–
ARC-AGI-1ARC Prize98.0%†–
ARC-AGI-2ARC Prize77.1%†–
ARC-AGI-3ARC Prize0.4%†–
CritPtArtificial Analysis17.7%†24.6%
CritPt v2 hard subset (AA)Artificial Analysis–49.5%
MysteryMechanismVals AI20.7%26.1%†
Arena ExpertArena (LMArena)1509†1515†
Chess PuzzlesEpoch AI Benchmarking Hub51.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub34.0%–
CL-benchEpoch AI Benchmarking Hub20.8%†–
CL-bench LifeEpoch AI Benchmarking Hub16.9%†–
LMCAEpoch AI Benchmarking Hub53.8%57.6%†
DTBenchEpoch AI Benchmarking Hub95.5%93.3%†
ForecastBenchForecastBench65.2%–
Show all 199 benchmarks
MetricPublisherGemini 3.1 Pro (high)Kimi K3.1 Pro
Coding
SciCodeSciCode58.7%†60.8%
WeirdMLWeirdML72.1%†–
GSO-BenchGSO-Bench22.6%†–
Arena CodingArena (LMArena)1520†1530†
Arena WebDevArena (LMArena)1446†1687†
LiveBench 2.0 CodingLiveBench–67.8%†
LiveBench 1.0 CodingLiveBench76.5%–
LiveCodeBenchVals AI88.5%–
IOIVals AI51.8%81.9%†
SWE-bench (Vals)Vals AI78.8%–
SWE-Bench ProScale AI SEAL46.1%†–
Code MigrationVals AI17.3%–
ProgramBenchVals AI0.0%–
Vibe Code Bench 1-100Vals AI6.7%–
Vibe Code Bench v1.1Vals AI32.0%84.9%†
SWE-Bench Pro (private)Scale AI SEAL32.2%†–
SWE Atlas v1.0: Codebase QnAScale AI SEAL13.5%†–
SWE Atlas v1.0: RefactoringScale AI SEAL33.8%†–
SWE Atlas v1.0: Test WritingScale AI SEAL29.8%†–
SWE Atlas v1.1Scale AI SEAL–61.1%
SWE Atlas v1.1: Codebase QnAScale AI SEAL–70.2%
SWE Atlas v1.1: Test WritingScale AI SEAL–58.9%
SWE Atlas v1.1: RefactoringScale AI SEAL–54.3%
MirrorCodeEpoch AI Benchmarking Hub8.9%–
DeepSWE v1.1Epoch AI Benchmarking Hub11.7%†–
ALE-BenchEpoch AI Benchmarking Hub1160.6†1932.8†
AlgoTuneAlgoTune2.0†–
WeirdML v3WeirdML–9.9%†
Terminal-Bench 4.0 (AA)Artificial Analysis4.0%†67.2%
Terminal-Bench 2.1 (AA)Artificial Analysis73.8%†–
GameBench 2 OverallDuelLab GameBench 2–78.3
GameBench 2 by reasoning settingDuelLab GameBench 2–84.0†
Design Arena WebsiteDesign Arena1226†1321
FrontierCode 1.1 (AA)Artificial Analysis–47.1%
FrontierCode 2.0 (AA)Artificial Analysis–25.4%
Agents & tools
Terminal-BenchTerminal-Bench80.2%†59.7%†
APEX-AgentsMercor35.1%†65.5%
Arena AgentArena (LMArena)-4.5†4.9†
LiveBench Long AgenticLiveBench–38.7%†
LiveBench BrowserLiveBench–75.9%†
LiveBench Agentic CodingLiveBench44.1%–
Terminal-Bench HardArtificial Analysis53.8%†–
τ²-Bench Telecom (AA)Artificial Analysis95.6%†–
Terminal-Bench 2.1 (Vals)Vals AI70.8%–
MCP AtlasScale AI SEAL78.2%–
HiL-BenchScale AI SEAL35.3%†61.3%
τ³-bench Bankingτ²-bench26.0%–
GDPval-AA v2.1, normalised scoreArtificial Analysis14.6%†67.3%
GDPval-AA v2.1Artificial Analysis799†1861
τ³-Banking (AA)Artificial Analysis21.4%†–
ITBench SRE (AA)Artificial Analysis30.3%†–
Analyst Agent (AA)Artificial Analysis41.3%†38.8%
APEX-Agents (AA)Artificial Analysis32.0%†–
Finance Agent v2Vals AI43.0%–
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 AI20.7%37.5%†
SREBenchVals AI0.0%27.1%†
Tax Agent BenchVals AI9.3%24.9%†
Terminal-Bench 2.0 (Vals)Vals AI67.4%–
Terminal-Bench 4.0 (Vals)Vals AI2.5%63.6%†
Terminal-Bench ScienceVals AI1.4%31.4%†
Arena SearchArena (LMArena)1209†–
Arena Agent Task CompletionArena (LMArena)-11.3†2.7†
BALROGBALROG57.0%†–
DeepResearch BenchDeepResearch Bench47.8%–
PostTrainBenchEpoch AI Benchmarking Hub18.1%†–
ExploitBenchEpoch AI Benchmarking Hub26.1%†–
METR Time HorizonsMETR77.0%†–
GBAEvalEpoch AI Benchmarking Hub0.8%†–
Vending-Bench 2Andon Labs911.2†–
AutomationBenchArtificial Analysis35.4%†73.3%
GDP.pdf (AA)Artificial Analysis17.8%†31.4%
Harvey LAB-AA v1.1Harvey0.0%†–
EnterpriseOps-GymArtificial Analysis42.2%†–
AA-Briefcase v1.1Artificial Analysis457†1674
Design Arena AgenticDesign Arena1088†1301
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%
MKA (AA)Artificial Analysis–43.9%
BrowseCompOpenAI31.2%†–
DeepSearchQAGoogle60.2%†–
FACTS SearchGoogle90.2%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.6%†–
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub95.6%–
ProofBenchVals AI26.0%†91.0%
LiveBench MathematicsLiveBench91.0%–
AIME (Vals)Vals AI98.1%–
AIME 2026MathArena98.3%–
HMMT February 2026MathArena94.7%–
USAMO 2026MathArena74.4%–
MathArena ApexMathArena60.9%–
ArXivMathMathArena–58.3%†
BrokenArXivMathArena–61.9%†
Arena MathsArena (LMArena)1488†–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub73.5%–
LiveBench 2.0 Data AnalysisLiveBench–79.1%†
LiveBench ResearchLiveBench–82.1%†
LiveBench 1.0 Data AnalysisLiveBench78.5%–
AA-Omniscience v1.1Artificial Analysis–29.9
MMLU-ProVals AI91.0%–
LegalBenchVals AI87.4%–
CorpFinVals AI64.5%–
TaxEvalVals AI72.9%–
MedQAVals AI96.4%–
PRBench FinanceScale AI SEAL41.9%†47.5%
PRBench LegalScale AI SEAL44.0%†47.9%
MultiNRCScale AI SEAL64.7%†–
BioMysteryBenchVals AI60.0%75.6%†
CaseLaw v2Vals AI64.8%–
Excel Modeling BenchmarkVals AI52.6%–
Excel Modeling Benchmark v1.1Vals AI–70.0%†
MedCodeVals AI59.1%–
MedScribeVals AI76.1%–
Public Benefits Bench v1.1Vals AI53.8%–
Access to Justice BenchmarkVals AI–69.5%†
Financial Coaching BenchVals AI66.7%–
DrugDiscoveryBenchScale AI SEAL41.9%63.4%†
EBR-benchEpoch AI Benchmarking Hub14.3%†–
GDP.pdfEpoch AI Benchmarking Hub17.0%–
AA-Omniscience v1.1: accuracyArtificial Analysis–48.9%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–62.7%
Global-MMLU-Lite (AA)Artificial Analysis93.2%†–
FACTS ParametricGoogle79.4%†–
Instruction following
LiveBench LanguageLiveBench85.4%–
LiveBench Instruction FollowingLiveBench79.1%–
IFBenchArtificial Analysis77.1%†–
MultiChallengeScale AI SEAL71.4%†–
TutorBenchScale AI SEAL53.0%†–
Arena Instruction FollowingArena (LMArena)1480†1487†
Human preference
Arena TextArena (LMArena)1487†1485†
EQ-Bench 4EQ-Bench1132†–
EQ-Bench Creative Writing v3EQ-Bench1491†2173
Arena Creative WritingArena (LMArena)1482†1453†
Arena Multi-turnArena (LMArena)1495†1475†
Arena Longer QueriesArena (LMArena)1499†1491†
Multimodal
Arena VisionArena (LMArena)1296†–
LiveBench DesignLiveBench–73.7%†
MMMU-ProArtificial Analysis82.4%†83.9%
MMMU-Pro (Vals)Vals AI88.2%–
MortgageTaxVals AI69.4%–
SAGEVals AI83.2%–
Humanity's Sixth SenseScale AI SEAL–33.2%†
VTBScale AI SEAL29.0%†–
GeoBenchGeoBench84.0%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub26.5%†–
Furniture AssemblyEpoch AI Benchmarking Hub26.7%–
VIALS-AAHandshake AI–45.3%
AA-3DArtificial Analysis–1112
FACTS MultimodalGoogle50.4%†–
Long context
AA-LCR v1.1Artificial Analysis82.0%†86.3%
Arena DocumentArena (LMArena)1459†–
MLCRArtificial Analysis11.1%†38.3%
FACTS GroundingGoogle56.6%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.2†161.4
LiveBench 2.0LiveBench–68.7%†
LiveBench 1.0LiveBench77.0%–
AA Intelligence Index v5.0.1Artificial Analysis–46.5
AA Intelligence Index v4.3.2Artificial Analysis29.7†55.1
AA Progress Index v1Artificial Analysis296.1†340.7
Vals IndexVals AI–62.5†
Vals Finance IndexVals AI–56.0%†
Vals Science IndexVals AI27.4%44.4%†
Vals Multimodal IndexVals AI56.1%–
Vals Legal IndexVals AI–67.0%†
AA Cyber IndexArtificial Analysis–64.1
Safety & honesty
FORTRESSScale AI SEAL29.8%†18.6%
MASKScale AI SEAL42.4%†–
DistressBenchScale AI SEAL68.8%†–
Metadata
AA Openness IndexArtificial Analysis–33.3

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

  • Kimi K3.1 Pro: BenchLeader Index 61.2 → 61.8.
  • Kimi K3.1 Pro: 1 score revision.
  • Kimi K3.1 Pro: 1 score revision.
  • Kimi K3.1 Pro: 1 new result (HiL-Bench).
  • Gemini 3.1 Pro (high): 4 new results (AIME 2026, HMMT February 2026, USAMO 2026…).
  • Kimi K3.1 Pro: 3 new results (PRBench Finance, PRBench Legal, FORTRESS); 2 score revisions.
  • 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.
  • Kimi K3.1 Pro: BenchLeader Index 61.3 → 61.8.

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

Gemini 3.1 Pro vs Kimi K3.1 Pro: questions

Is Gemini 3.1 Pro better than Kimi K3.1 Pro?
Gemini 3.1 Pro (high) and Kimi K3.1 Pro are neck and neck on quality (60.4 vs 61.8, within the ±4.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Gemini 3.1 Pro vs Kimi K3.1 Pro: which is cheaper, and will that change?
Kimi K3.1 Pro 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 Kimi K3.1 Pro better for coding?
Kimi K3.1 Pro scores higher in coding (60 vs 59 on the category index, where 50 is average).
Which is faster, Gemini 3.1 Pro or Kimi K3.1 Pro?
Gemini 3.1 Pro streams 3×+ faster (111 vs 30 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.1 Pro or Kimi K3.1 Pro better for agents and tool use?
Kimi K3.1 Pro scores higher in agentic tasks (65 vs 57 on the category index, where 50 is average).
More questions (3)
Which is better for long documents?
Both accept 1,048,576 tokens of context.
Which has lower latency?
Gemini 3.1 Pro answers first: 15.2 s against 157.4 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.
When was Kimi K3.1 Pro released?
Kimi K3.1 Pro was released on 23 Oct 2026.