BenchLeader

Kimi K2.7 Code vs MiniMax M3.1 Flash

Full profiles: Kimi K2.7 Code (Moonshot AI) and MiniMax M3.1 Flash (MiniMax): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Kimi K2.7 Code and MiniMax M3.1 Flash are neck and neck on quality (53.9 vs 54.3 on the BenchLeader Index, inside the ±6.5 margin), and MiniMax M3.1 Flash is 6.5× cheaper at $0.262 vs $1.71 per 1M tokens blended. Choose Kimi K2.7 Code for reasoning (53 vs 50); choose MiniMax M3.1 Flash for coding (55 vs 52) and agents & tools (55 vs 52), where it also streams ~2× faster.

Key facts (as of 16 Nov 2026)

  • Kimi K2.7 Code scores 53.9 on the BenchLeader Index and MiniMax M3.1 Flash scores 54.3 (BenchLeader, 16 Nov 2026).
  • Kimi K2.7 Code costs $1.71 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).
  • MiniMax M3.1 Flash streams ~2× faster than Kimi K2.7 Code (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 17 benchmarks both models have, MiniMax M3.1 Flash leads 16 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Kimi K2.7 Code is rated 1474 and MiniMax M3.1 Flash 1584 (LMArena, as published by 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 52 category score; Arena WebDev 1584 vs 1474Medium
Agents & tool useMiniMax M3.1 Flash55 vs 52 category score; GDPval-AA v2.1, normalised score 47.9% vs 26.9%Medium
ReasoningKimi K2.7 Code53 vs 50 category score; HLE-Diamond (AA) 14.8% vs 28.1%Medium
KnowledgeEither45 vs 46 category scoreEither
Long documentsEither64 vs 65 category score; AA-LCR v1.1 79.3% vs 79.7%Either
Lowest costMiniMax M3.1 Flash$0.262 vs $1.71 per 1M blended; agentic coding session $0.011 vs $0.073–
Fastest first answerKimi K2.7 Code29.6 s (Kimi K2.7 Code) 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 K2.7 Code and MiniMax M3.1 Flash are neck and neck on quality (53.9 vs 54.3, within the ±6.5 margin).
  • Kimi K2.7 Code is stronger in reasoning.
  • MiniMax M3.1 Flash is stronger in agents & tools, coding, knowledge, long context.
  • MiniMax M3.1 Flash is 6.5× cheaper ($0.262 vs $1.71 per 1M blended).
  • MiniMax M3.1 Flash streams 2.8× faster (151 vs 55 tokens per second).

At a glance

SpecKimi K2.7 CodeMiniMax M3.1 Flash
DeveloperMoonshot AIMiniMax
Released12 Jun 202619 Oct 2026
Context window (tokens)262,1441,000,000
Compared atKimi K2.7 CodeMiniMax M3.1 Flash
Open weightsYesYes
Price in / out / cached input per 1M$0.950 / $4.00 / $0.190$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 K2.7 CodeMiniMax M3.1 FlashLeader
Reasoning53.050.1Kimi K2.7 Code
Coding51.955.4MiniMax M3.1 Flash
Agents & tools52.155.2MiniMax M3.1 Flash
Maths51.9–not comparable
Knowledge45.445.9level
Instruction following62.9–not comparable
Multimodal–61.5not comparable
Long context64.364.5level

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 K2.7 Code, Reasoning: 53.0Kimi K2.7 Code, Coding: 51.9Kimi K2.7 Code, Agents & tools: 52.1Kimi K2.7 Code, Knowledge: 45.4Kimi K2.7 Code, Long context: 64.3MiniMax 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 17 benchmarks both have, Kimi K2.7 Code leads 0, MiniMax M3.1 Flash leads 16 and 1 is a tie.

Overall indexKimi K2.7 CodeMiniMax M3.1 FlashLeader
BenchLeader Index53.954.3neck 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 K2.7 CodeMiniMax M3.1 Flash
Blended price per 1M tokens$1.71$0.262
Input / output per 1M$0.950 / $4.00$0.150 / $0.600
Cached input per 1M$0.190$0.015
Price per task: chat reply$0.0016$0.0002
Price per task: summarize a 30-page report$0.014$0.0022
Price per task: code edit$0.012$0.0018
Price per task: agentic coding session$0.073$0.011
Price per task: structured extraction$0.0027$0.0004
Agentic coding session, input mostly cached$0.039$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 speed55 tok/s151 tok/s
Time to first answer29.6 s43.3 s
Time to a complete answer, last measured 13 Nov 2026102.4 s141.5 s

Each model is compared at its best-ranked reasoning-effort setting. Kimi K2.7 Code scores 53.9 and takes 30 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

100 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 K2.7 CodeMiniMax M3.1 Flash
BenchLeader IndexBenchLeader53.954.3
Agents & tools scoreBenchLeader52.155.2
Coding scoreBenchLeader51.955.4
Instruction following scoreBenchLeader62.9–
Knowledge scoreBenchLeader45.445.9
Long context scoreBenchLeader64.364.5
Maths scoreBenchLeader51.9–
Reasoning scoreBenchLeader53.050.1
Multimodal scoreBenchLeader–61.5
Blended price $/MBenchLeader$1.71$0.262
Output speedBenchLeader55 tok/s151 tok/s
Time to first answerBenchLeader29.6 s43.3 s
Context windowBenchLeader262,144 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub87.9%–
SimpleBenchSimpleBench57.9%–
LiveBench 2.0 ReasoningLiveBench–82.9%†
LiveBench 1.0 ReasoningLiveBench82.8%–
GPQA Diamond (AA)Artificial Analysis89.6%–
Humanity's Last Exam (AA)Artificial Analysis35.0%48.0%
HLE-Diamond (AA)Artificial Analysis14.8%28.1%
CritPtArtificial Analysis10.0%22.3%
CritPt v2 hard subset (AA)Artificial Analysis–32.5%
Chess PuzzlesEpoch AI Benchmarking Hub14.0%–
Coding
SciCodeSciCode47.8%–
WeirdMLWeirdML54.1%–
FrontierCodeCognition30.1%–
Arena WebDevArena (LMArena)14741584
LiveBench 2.0 CodingLiveBench–68.8%†
LiveBench 1.0 CodingLiveBench74.0%–
SciCode (AA)Artificial Analysis47.8%53.4%
LiveCodeBenchVals AI82.0%–
SWE-bench (Vals)Vals AI78.2%–
Code MigrationVals AI25.4%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI47.2%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%†
Show all 100 benchmarks
MetricPublisherKimi K2.7 CodeMiniMax M3.1 Flash
Coding
Surface Evolver BenchEpoch AI Benchmarking Hub48.8%–
DeepSWE v1.1Epoch AI Benchmarking Hub30.5%–
ALE-BenchEpoch AI Benchmarking Hub886.2–
Terminal-Bench 4.0 (AA)Artificial Analysis1.0%25.8%
Terminal-Bench 2.1 (AA)Artificial Analysis67.4%–
GameBench 2 by reasoning settingDuelLab GameBench 2–30.3†
Design Arena WebsiteDesign Arena12581277
FrontierCode 1.1 (AA)Artificial Analysis–38.6%
FrontierCode 2.0 (AA)Artificial Analysis–20.8%
Agents & tools
APEX-AgentsMercor37.6%–
Arena AgentArena (LMArena)–-2.7
LiveBench Long AgenticLiveBench–25.7%†
LiveBench BrowserLiveBench–80.6%†
LiveBench Agentic CodingLiveBench45.7%–
Terminal-Bench HardArtificial Analysis44.7%–
τ²-Bench Telecom (AA)Artificial Analysis90.1%–
Terminal-Bench 2.1 (Vals)Vals AI67.0%–
HiL-BenchScale AI SEAL–65.7%
GDPval-AA v2.1, normalised scoreArtificial Analysis26.9%47.9%
GDPval-AA v2.1Artificial Analysis10461465
τ³-Banking (AA)Artificial Analysis20.2%–
Finance Agent v2.1Vals AI–58.8%†
Harvey's Legal Agent Benchmark v1.1Vals AI–7.5%†
Legal Research BenchVals AI–34.1%†
SkillsBenchVals AI50.0%–
Tax Agent BenchVals AI–32.1%†
Terminal-Bench 4.0 (Vals)Vals AI–25.3%†
Arena Agent Task CompletionArena (LMArena)–-0.7
GBAEvalEpoch AI Benchmarking Hub0.8%–
Vending-Bench 2Andon Labs5082.9–
AutomationBenchArtificial Analysis24.4%72.5%
GDP.pdf (AA)Artificial Analysis11.2%20.8%
EnterpriseOps-GymArtificial Analysis40.2%–
AA-Briefcase v1.1Artificial Analysis8581474
GDPxGDPx by SemiAnalysis–4.0%†
Design Arena AgenticDesign Arena11581252
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–3.3%
MKA (AA)Artificial Analysis–33.5%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub54.0%–
FrontierMath Tier 4Epoch AI Benchmarking Hub12.2%–
OTIS Mock AIMEEpoch AI Benchmarking Hub95.6%–
LiveBench MathematicsLiveBench79.6%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub36.5%–
LiveBench 2.0 Data AnalysisLiveBench–71.4%†
LiveBench ResearchLiveBench–76.7%†
LiveBench 1.0 Data AnalysisLiveBench62.7%–
AA-Omniscience v1.1Artificial Analysis–-6.4
PRBench FinanceScale AI SEAL–45.6%
PRBench LegalScale AI SEAL–45.1%
Excel Modeling Benchmark v1.1Vals AI–67.8%†
Access to Justice BenchmarkVals AI–73.3%†
DrugDiscoveryBenchScale AI SEAL35.3%†–
AA-Omniscience v1.1: accuracyArtificial Analysis–45.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–6.3%
Instruction following
LiveBench LanguageLiveBench77.9%–
LiveBench Instruction FollowingLiveBench56.3%–
IFBenchArtificial Analysis63.1%–
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 Analysis79.3%79.7%
MLCRArtificial Analysis12.2%16.7%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub151.2–
LiveBench 2.0LiveBench–63.7%†
LiveBench 1.0LiveBench68.4%–
AA Intelligence Index v5.0.1Artificial Analysis–29.1
AA Intelligence Index v4.3.2Artificial Analysis25.842.7
AA Progress Index v1Artificial Analysis287.6317.6
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

  • MiniMax M3.1 Flash: BenchLeader Index 53.7 → 54.3.
  • Kimi K2.7 Code: 1 score revision.
  • MiniMax M3.1 Flash: BenchLeader Index 54.3 → 53.7.
  • 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).
  • MiniMax M3.1 Flash: BenchLeader Index 52.0 → 53.0.
  • Kimi K2.7 Code: 1 score revision.
  • MiniMax M3.1 Flash: 2 new results (PRBench Finance, PRBench Legal).

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

Kimi K2.7 Code vs MiniMax M3.1 Flash: questions

Is Kimi K2.7 Code better than MiniMax M3.1 Flash?
Kimi K2.7 Code and MiniMax M3.1 Flash are neck and neck on quality (53.9 vs 54.3, within the ±6.5 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.
Kimi K2.7 Code vs MiniMax M3.1 Flash: which is cheaper, and will that change?
MiniMax M3.1 Flash is cheaper today: $0.262 against $1.71 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Kimi K2.7 Code or MiniMax M3.1 Flash better for coding?
MiniMax M3.1 Flash scores higher in coding (55 vs 52 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1474 for Kimi K2.7 Code against 1584 for MiniMax M3.1 Flash.
Which is faster, Kimi K2.7 Code or MiniMax M3.1 Flash?
MiniMax M3.1 Flash streams ~2× faster (151 vs 55 output tokens per second, Artificial Analysis 7-day median).
Is Kimi K2.7 Code or MiniMax M3.1 Flash better for agents and tool use?
MiniMax M3.1 Flash scores higher in agentic tasks (55 vs 52 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (64 vs 65). MiniMax M3.1 Flash accepts more context: 1,000,000 against 262,144 tokens for Kimi K2.7 Code.
Which has lower latency?
Kimi K2.7 Code answers first: 29.6 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 K2.7 Code vs MiniMax M3.1 Flash?
Across the 17 benchmarks both have, Kimi K2.7 Code leads 0, MiniMax M3.1 Flash leads 16 and 1 is a tie.
When was MiniMax M3.1 Flash released?
MiniMax M3.1 Flash was released on 19 Oct 2026.