BenchLeader

Kimi K2 Thinking vs MiniMax M3.1 Flash

Full profiles: Kimi K2 Thinking (Moonshot AI) and MiniMax M3.1 Flash (MiniMax): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, Kimi K2 Thinking and MiniMax M3.1 Flash are neck and neck on quality (52.3 vs 54.3 on the BenchLeader Index, inside the ±5.6 margin), and MiniMax M3.1 Flash is 4.1× cheaper at $0.262 vs $1.07 per 1M tokens blended. Choose Kimi K2 Thinking for knowledge (51 vs 46) and fast first answers (25.1 s vs 43.3 s); choose MiniMax M3.1 Flash for coding (55 vs 49), long context (65 vs 61), and agents & tools (55 vs 51).

Key facts (as of 16 Nov 2026)

  • Kimi K2 Thinking scores 52.3 on the BenchLeader Index and MiniMax M3.1 Flash scores 54.3 (BenchLeader, 16 Nov 2026).
  • Kimi K2 Thinking costs $1.07 per 1M tokens blended (list price, 16 Nov 2026).
  • MiniMax M3.1 Flash costs $0.262 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 8 benchmarks both models have, MiniMax M3.1 Flash leads 7 (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
CodingMiniMax M3.1 Flash55 vs 49 category score; Design Arena Website 1277 vs 1105Medium
Agents & tool useMiniMax M3.1 Flash55 vs 51 category scoreMedium
ReasoningMiniMax M3.1 Flash50 vs 47 category score; Humanity's Last Exam (AA) 48.0% vs 23.8%Medium
KnowledgeKimi K2 Thinking51 vs 46 category score; PRBench Finance 43.4% vs 45.6%Medium
Long documentsMiniMax M3.1 Flash65 vs 61 category score; AA-LCR v1.1 79.7% vs 72.0%Medium
Lowest costMiniMax M3.1 Flash$0.262 vs $1.07 per 1M blended; agentic coding session $0.011 vs $0.046–
Fastest first answerKimi K2 Thinking25.1 s (Kimi K2 Thinking (thinking)) vs 43.3 s (MiniMax M3.1 Flash) 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

  • Kimi K2 Thinking (thinking) and MiniMax M3.1 Flash are neck and neck on quality (52.3 vs 54.3, within the ±5.6 margin).
  • Kimi K2 Thinking (thinking) is stronger in knowledge.
  • MiniMax M3.1 Flash is stronger in agents & tools, coding, long context, reasoning.
  • MiniMax M3.1 Flash is 4.1× cheaper ($0.262 vs $1.07 per 1M blended).

At a glance

SpecKimi K2 ThinkingMiniMax M3.1 Flash
DeveloperMoonshot AIMiniMax
Released6 Nov 202519 Oct 2026
Context window (tokens)262,1441,000,000
Compared atKimi K2 Thinking (thinking)MiniMax M3.1 Flash
Open weightsYesYes
Price in / out / cached input per 1M$0.600 / $2.50 / $0.150$0.150 / $0.600 / $0.015

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.

CategoryKimi K2 Thinking (thinking)MiniMax M3.1 FlashLeader
Reasoning46.950.1MiniMax M3.1 Flash
Coding49.255.4MiniMax M3.1 Flash
Agents & tools51.455.2MiniMax M3.1 Flash
Maths50.5–not comparable
Knowledge51.045.9Kimi K2 Thinking
Instruction following59.3–not comparable
Multimodal–61.5not comparable
Long context60.564.5MiniMax M3.1 Flash

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 & toolsKnowledgeLong contextKimi K2 Thinking, Reasoning: 46.9Kimi K2 Thinking, Coding: 49.2Kimi K2 Thinking, Agents & tools: 51.4Kimi K2 Thinking, Knowledge: 51.0Kimi K2 Thinking, Long context: 60.5MiniMax M3.1 Flash, Reasoning: 50.1MiniMax M3.1 Flash, Coding: 55.4MiniMax M3.1 Flash, Agents & tools: 55.2MiniMax M3.1 Flash, Knowledge: 45.9MiniMax M3.1 Flash, Long context: 64.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 8 benchmarks both have, Kimi K2 Thinking leads 0, MiniMax M3.1 Flash leads 7 and 1 is a tie.

Overall indexKimi K2 Thinking (thinking)MiniMax M3.1 FlashLeader
BenchLeader Index52.354.3neck 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.

MeasureKimi K2 Thinking (thinking)MiniMax M3.1 Flash
Blended price per 1M tokens$1.07$0.262
Input / output per 1M$0.600 / $2.50$0.150 / $0.600
Cached input per 1M$0.150$0.015
Price per task: chat reply$0.0010$0.0002
Price per task: summarize a 30-page report$0.0087$0.0022
Price per task: code edit$0.0074$0.0018
Price per task: agentic coding session$0.046$0.011
Price per task: structured extraction$0.0017$0.0004
Agentic coding session, input mostly cached$0.026$0.0053
Cost per benchmark task (AA Index)–$0.491
Output tokens per task (AA Index)–138k
Of which reasoning–103k
Time per task (AA Index)–15 min
Output speed130 tok/s151 tok/s
Time to first answer25.1 s43.3 s
Time to a complete answer, last measured 13 Nov 202646.4 s141.5 s

Each model is compared at its best-ranked reasoning-effort setting. Kimi K2 Thinking (thinking) scores 52.3 and takes 25 s to its first answer token. MiniMax M3.1 Flash scores 54.3 and takes 43 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

94 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.

MetricPublisherKimi K2 Thinking (thinking)MiniMax M3.1 Flash
BenchLeader IndexBenchLeader52.354.3
Agents & tools scoreBenchLeader51.455.2
Coding scoreBenchLeader49.255.4
Instruction following scoreBenchLeader59.3–
Knowledge scoreBenchLeader51.045.9
Long context scoreBenchLeader60.564.5
Maths scoreBenchLeader50.5–
Reasoning scoreBenchLeader46.950.1
Multimodal scoreBenchLeader–61.5
Blended price $/MBenchLeader$1.07$0.262
Output speedBenchLeader130 tok/s151 tok/s
Time to first answerBenchLeader25.1 s43.3 s
Context windowBenchLeader262,144 tokens1,000,000 tokens
Reasoning
SimpleBenchSimpleBench39.6%–
LiveBench 2.0 ReasoningLiveBench–82.9%†
GPQA Diamond (AA)Artificial Analysis83.8%–
Humanity's Last Exam (AA)Artificial Analysis23.8%48.0%
HLE-Diamond (AA)Artificial Analysis–28.1%
GPQA Diamond (Vals)Vals AI78.5%–
Kagi LLM BenchmarkKagi LLM Benchmark64.4%–
CritPtArtificial Analysis2.6%22.3%
CritPt v2 hard subset (AA)Artificial Analysis–32.5%
CL-benchEpoch AI Benchmarking Hub17.6%–
Coding
WeirdMLWeirdML42.8%–
Arena WebDevArena (LMArena)–1584
LiveBench 2.0 CodingLiveBench–68.8%†
SciCode (AA)Artificial Analysis–53.4%
LiveCodeBenchVals AI63.1%–
SWE-bench (Vals)Vals AI60.2%–
SWE-bench Verified (bash only)SWE-bench63.4%–
SWE-bench Verified (any scaffold)SWE-bench63.4%–
Vibe Code Bench v1.1Vals AI–73.9%†
Vibe Code Bench 1-100 v1.1Vals AI–19.8%†
SWE-Bench Pro V2Scale AI SEAL–96.6%†
SWE-Bench Pro V2 HARDScale AI SEAL–84.3%†
ALE-BenchEpoch AI Benchmarking Hub597.5–
Terminal-Bench 4.0 (AA)Artificial Analysis–25.8%
GameBench 2 by reasoning settingDuelLab GameBench 2–30.3†
Show all 94 benchmarks
MetricPublisherKimi K2 Thinking (thinking)MiniMax M3.1 Flash
Coding
Design Arena WebsiteDesign Arena11051277
FrontierCode 1.1 (AA)Artificial Analysis–38.6%
FrontierCode 2.0 (AA)Artificial Analysis–20.8%
LiveCodeBench (AA)Artificial Analysis85.3%–
Agents & tools
Terminal-BenchTerminal-Bench35.7%–
Arena AgentArena (LMArena)–-2.7
LiveBench Long AgenticLiveBench–25.7%†
LiveBench BrowserLiveBench–80.6%†
Terminal-Bench HardArtificial Analysis31.1%–
τ²-Bench Telecom (AA)Artificial Analysis93.0%–
HiL-BenchScale AI SEAL–65.7%
GDPval-AA v2.1, normalised scoreArtificial Analysis–47.9%
GDPval-AA v2.1Artificial Analysis–1465
Finance Agent v2.1Vals AI–58.8%†
Harvey's Legal Agent Benchmark v1.1Vals AI–7.5%†
Legal Research BenchVals AI–34.1%†
Poker AgentVals AI1011.6%–
Tax Agent BenchVals AI–32.1%†
Terminal-Bench 2.0 (Vals)Vals AI37.1%–
Terminal-Bench 4.0 (Vals)Vals AI–25.3%†
Arena Agent Task CompletionArena (LMArena)–-0.7
METR Time HorizonsMETR59.2%–
AutomationBenchArtificial Analysis–72.5%
GDP.pdf (AA)Artificial Analysis–20.8%
AA-Briefcase v1.1Artificial Analysis–1474
GDPxGDPx by SemiAnalysis–4.0%†
Design Arena AgenticDesign Arena–1252
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–3.3%
MKA (AA)Artificial Analysis–33.5%
Maths
AIME (Vals)Vals AI85.4%–
MGSMVals AI90.2%–
MathArena ApexMathArena0.0%–
AIME 2025 (AA)Artificial Analysis94.7%–
Knowledge
LiveBench 2.0 Data AnalysisLiveBench–71.4%†
LiveBench ResearchLiveBench–76.7%†
AA-Omniscience v1.1Artificial Analysis–-6.4
MMLU-ProVals AI81.1%–
LegalBenchVals AI80.2%–
CorpFinVals AI60.6%–
TaxEvalVals AI71.7%–
MedQAVals AI92.6%–
PRBench FinanceScale AI SEAL43.4%45.6%
PRBench LegalScale AI SEAL40.9%45.1%
CaseLaw v2Vals AI65.7%–
Excel Modeling Benchmark v1.1Vals AI–67.8%†
Access to Justice BenchmarkVals AI–73.3%†
AA-Omniscience v1.1: accuracyArtificial Analysis–45.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–6.3%
Global-MMLU-Lite (AA)Artificial Analysis73.5%–
Instruction following
IFBenchArtificial Analysis68.1%–
MultiChallengeScale AI SEAL55.4%–
Human preference
EQ-Bench Creative Writing v3EQ-Bench1631–
Multimodal
LiveBench DesignLiveBench–71.2%†
MMMU-ProArtificial Analysis–79.1%
SAGEVals AI–85.3%†
VIALS-AAHandshake AI–29.8%
Long context
AA-LCR v1.1Artificial Analysis72.0%79.7%
MLCRArtificial Analysis–16.7%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub145.4–
LiveBench 2.0LiveBench–63.7%†
AA Intelligence Index v5.0.1Artificial Analysis–29.1
AA Intelligence Index v4.3.2Artificial Analysis22.042.7
AA Progress Index v1Artificial Analysis264.7317.6
Vals IndexVals AI–53.8†
Vals Finance IndexVals AI–55.9%†
Vals Router IndexVals AI–53.8%
Vals Legal IndexVals AI–67.1%†
Safety & honesty
FORTRESSScale AI SEAL–52.1%
Metadata
AA Openness IndexArtificial Analysis27.827.8

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 K2 Thinking (thinking): BenchLeader Index 51.8 → 52.3.
  • MiniMax M3.1 Flash: BenchLeader Index 53.7 → 54.3.
  • Kimi K2 Thinking (thinking): 2 new results (Global-MMLU-Lite (AA), AIME 2025 (AA)).
  • Kimi K2 Thinking (thinking): BenchLeader Index 53.1 → 51.8.
  • MiniMax M3.1 Flash: BenchLeader Index 54.3 → 53.7.
  • Kimi K2 Thinking (thinking): 1 new result (SimpleBench).
  • MiniMax M3.1 Flash: 1 score revision.
  • MiniMax M3.1 Flash: 6 score revisions.
  • MiniMax M3.1 Flash: BenchLeader Index 53.0 → 54.3.
  • MiniMax M3.1 Flash: 1 new result (HiL-Bench).

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

Kimi K2 Thinking vs MiniMax M3.1 Flash: questions

Is Kimi K2 Thinking better than MiniMax M3.1 Flash?
Kimi K2 Thinking (thinking) and MiniMax M3.1 Flash are neck and neck on quality (52.3 vs 54.3, within the ±5.6 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.
Kimi K2 Thinking vs MiniMax M3.1 Flash: which is cheaper, and will that change?
MiniMax M3.1 Flash is cheaper today: $0.262 against $1.07 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Kimi K2 Thinking or MiniMax M3.1 Flash better for coding?
MiniMax M3.1 Flash scores higher in coding (55 vs 49 on the category index, where 50 is average).
Which is faster, Kimi K2 Thinking or MiniMax M3.1 Flash?
MiniMax M3.1 Flash streams faster (151 vs 130 output tokens per second, Artificial Analysis 7-day median).
Is Kimi K2 Thinking or MiniMax M3.1 Flash better for agents and tool use?
MiniMax M3.1 Flash scores higher in agentic tasks (55 vs 51 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
MiniMax M3.1 Flash scores higher on long-context benchmarks (65 vs 61). MiniMax M3.1 Flash accepts more context: 1,000,000 against 262,144 tokens for Kimi K2 Thinking.
Which has lower latency?
Kimi K2 Thinking answers first: 25.1 s against 43.3 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 Kimi K2 Thinking vs MiniMax M3.1 Flash?
Across the 8 benchmarks both have, Kimi K2 Thinking leads 0, MiniMax M3.1 Flash leads 7 and 1 is a tie.
When was MiniMax M3.1 Flash released?
MiniMax M3.1 Flash was released on 19 Oct 2026.