BenchLeader

MiMo-V2.6-Pro vs Qwen3.6 Max

Full profiles: MiMo-V2.6-Pro (Xiaomi) and Qwen3.6 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 7 sources

As of 16 Nov 2026, Qwen3.6 Max is ahead of MiMo-V2.6-Pro on quality (62.1 vs 57.5 on the BenchLeader Index), but MiMo-V2.6-Pro is 5.4× cheaper at $0.544 vs $2.92 per 1M tokens blended. Choose MiMo-V2.6-Pro for long context (68 vs 65), coding (59 vs 56), and human preference (67 vs 65); choose Qwen3.6 Max for knowledge (60 vs 42), agents & tools (72 vs 57), and reasoning (61 vs 50).

Key facts (as of 16 Nov 2026)

  • MiMo-V2.6-Pro scores 57.5 on the BenchLeader Index and Qwen3.6 Max scores 62.1 (BenchLeader, 16 Nov 2026).
  • MiMo-V2.6-Pro costs $0.544 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.6 Max costs $2.92 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 13 benchmarks both models have, MiMo-V2.6-Pro leads 12 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, MiMo-V2.6-Pro is rated 1625 and Qwen3.6 Max 1482 (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
CodingMiMo-V2.6-Pro59 vs 56 category score; Arena WebDev 1625 vs 1482Medium
Agents & tool useQwen3.6 Max72 vs 57 category scoreHigh
MathsMiMo-V2.6-Pro66 vs 64 category score; Arena Maths 1484 vs 1471Medium
ReasoningQwen3.6 Max61 vs 50 category score; Arena Hard Prompts 1481 vs 1504High
KnowledgeQwen3.6 Max60 vs 42 category scoreHigh
Long documentsMiMo-V2.6-Pro68 vs 65 category score; AA-LCR v1.1 86.3% vs 80.7%Medium
Chat quality (human preference)MiMo-V2.6-Pro67 vs 65 on Arena votesMedium
Lowest costMiMo-V2.6-Pro$0.548 vs $2.92 per 1M blended; agentic coding session $0.030 vs $0.109–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Qwen3.6 Max (max) leads on quality: 62.1 vs 57.5.
  • MiMo-V2.6-Pro is stronger in coding, human preference, long context, maths.
  • Qwen3.6 Max (max) is stronger in agents & tools, knowledge, reasoning.
  • MiMo-V2.6-Pro is 5.4× cheaper ($0.544 vs $2.92 per 1M blended).

At a glance

SpecMiMo-V2.6-ProQwen3.6 Max
DeveloperXiaomiAlibaba
Released21 Sep 202620 Apr 2026
Context window (tokens)1,048,576262,144
Compared atMiMo-V2.6-ProQwen3.6 Max (max)
Open weightsYesNo
Price in / out / cached input per 1M$0.440 / $0.870 / $0.0036$1.30 / $7.80 / $0.130

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.

CategoryMiMo-V2.6-ProQwen3.6 Max (max)Leader
Reasoning49.960.8Qwen3.6 Max
Coding58.855.9MiMo-V2.6-Pro
Agents & tools57.172.1Qwen3.6 Max
Maths65.564.4MiMo-V2.6-Pro
Knowledge42.359.7Qwen3.6 Max
Instruction following–74.7not comparable
Human preference67.064.5MiMo-V2.6-Pro
Multimodal60.2–not comparable
Long context67.965.0MiMo-V2.6-Pro

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 contextHumanpreferenceMiMo-V2.6-Pro, Reasoning: 49.9MiMo-V2.6-Pro, Coding: 58.8MiMo-V2.6-Pro, Agents & tools: 57.1MiMo-V2.6-Pro, Maths: 65.5MiMo-V2.6-Pro, Knowledge: 42.3MiMo-V2.6-Pro, Long context: 67.9MiMo-V2.6-Pro, Human preference: 67.0Qwen3.6 Max, Reasoning: 60.8Qwen3.6 Max, Coding: 55.9Qwen3.6 Max, Agents & tools: 72.1Qwen3.6 Max, Maths: 64.4Qwen3.6 Max, Knowledge: 59.7Qwen3.6 Max, Long context: 65.0Qwen3.6 Max, Human preference: 64.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 13 benchmarks both have, MiMo-V2.6-Pro leads 12, Qwen3.6 Max leads 1. Independent sources split: MiMo-V2.6-Pro leads on Arena Text; Qwen3.6 Max leads on BenchLeader Index.

Overall indexMiMo-V2.6-ProQwen3.6 Max (max)Leader
BenchLeader Index57.562.1Qwen3.6 Max
Arena Text14801460MiMo-V2.6-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.

MeasureMiMo-V2.6-ProQwen3.6 Max (max)
Blended price per 1M tokens$0.548$2.92
Input / output per 1M$0.440 / $0.870$1.30 / $7.80
Cached input per 1M$0.0036$0.130
Price per task: chat reply$0.0004$0.0029
Price per task: summarize a 30-page report$0.0058$0.020
Price per task: code edit$0.0039$0.019
Price per task: agentic coding session$0.030$0.109
Price per task: structured extraction$0.0011$0.0042
Agentic coding session, input mostly cached$0.010$0.057
Cost per benchmark task (AA Index)$0.257–
Output tokens per task (AA Index)121k–
Of which reasoning86k–
Time per task (AA Index)38 min–
Output speed54 tok/s–
Time to first answer42.3 s–
Time to a complete answer, last measured 13 Nov 202695.7 s–

Each model is compared at its best-ranked reasoning-effort setting. MiMo-V2.6-Pro scores 57.5 and takes 42 s to its first answer token. Qwen3.6 Max (max) scores 62.1. 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

111 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.

MetricPublisherMiMo-V2.6-ProQwen3.6 Max (max)
BenchLeader IndexBenchLeader57.562.1
Agents & tools scoreBenchLeader57.172.1
Coding scoreBenchLeader58.855.9
Human preference scoreBenchLeader67.064.5
Knowledge scoreBenchLeader42.359.7
Long context scoreBenchLeader67.965.0
Maths scoreBenchLeader65.564.4
Multimodal scoreBenchLeader60.2–
Reasoning scoreBenchLeader49.960.8
Instruction following scoreBenchLeader–74.7
Blended price $/MBenchLeader$0.548$2.92
Output speedBenchLeader54 tok/s–
Time to first answerBenchLeader42.3 s–
Context windowBenchLeader1,048,576 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–87.4%
SimpleBenchSimpleBench–63.0%
Arena Hard PromptsArena (LMArena)15041481
LiveBench 2.0 ReasoningLiveBench79.6%†–
GPQA Diamond (AA)Artificial Analysis–88.8%
Humanity's Last Exam (AA)Artificial Analysis49.4%30.8%
HLE-Diamond (AA)Artificial Analysis15.2%–
CritPtArtificial Analysis26.6%3.7%
CritPt v2 hard subset (AA)Artificial Analysis34.0%–
MysteryMechanismVals AI15.3%–
Arena ExpertArena (LMArena)15261497
Mystery Game PuzzlesEpoch AI Benchmarking Hub–19.0%†
LMCAEpoch AI Benchmarking Hub–42.5%
DTBenchEpoch AI Benchmarking Hub–87.2%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–76.7%
SciCodeSciCode60.9%–
Arena CodingArena (LMArena)15381510
Arena WebDevArena (LMArena)16251482
LiveBench 2.0 CodingLiveBench64.5%†–
IOIVals AI39.3%–
SWE-bench (Vals)Vals AI–72.8%
Code MigrationVals AI43.0%–
Code Migration v1.1Vals AI48.8%–
ProgramBenchVals AI0.5%–
SWE-bench MultimodalVals AI41.3%–
Show all 111 benchmarks
MetricPublisherMiMo-V2.6-ProQwen3.6 Max (max)
Coding
Vibe Code Bench v1.1Vals AI85.2%–
Vibe Code Bench 1-100 v1.1Vals AI26.4%–
ALE-BenchEpoch AI Benchmarking Hub1158.1–
Terminal-Bench 4.0 (AA)Artificial Analysis34.9%–
GameBench 2 by reasoning settingDuelLab GameBench 249.8†–
Design Arena WebsiteDesign Arena1311–
FrontierCode 1.1 (AA)Artificial Analysis45.4%–
FrontierCode 2.0 (AA)Artificial Analysis24.0%–
Agents & tools
Terminal-BenchTerminal-Bench27.0%†–
APEX-AgentsMercor54.4%–
Arena AgentArena (LMArena)2.4–
LiveBench Long AgenticLiveBench36.4%†–
LiveBench BrowserLiveBench77.3%†–
Terminal-Bench HardArtificial Analysis–43.9%
τ²-Bench Telecom (AA)Artificial Analysis–95.9%
Terminal-Bench 2.1 (Vals)Vals AI67.8%–
GDPval-AA v2.1, normalised scoreArtificial Analysis59.1%–
GDPval-AA v2.1Artificial Analysis1692–
Analyst Agent (AA)Artificial Analysis37.5%–
CyberBenchVals AI72.9%–
Finance Agent v2Vals AI57.3%–
Finance Agent v2.1Vals AI64.3%–
Harvey's Legal Agent Benchmark v1.1Vals AI13.8%–
Harvey's Legal Agent Benchmark v1Vals AI10.8%–
Legal Research BenchVals AI47.1%–
SREBenchVals AI3.0%–
Tax Agent BenchVals AI32.4%–
Terminal-Bench 2.0 (Vals)Vals AI–51.7%
Terminal-Bench 4.0 (Vals)Vals AI31.3%–
Terminal-Bench ScienceVals AI2.9%–
Arena Agent Task CompletionArena (LMArena)5–
Vending-Bench 2Andon Labs–4254.2
AutomationBenchArtificial Analysis58.6%–
GDP.pdf (AA)Artificial Analysis19.2%–
AA-Briefcase v1.1Artificial Analysis1512–
Design Arena AgenticDesign Arena1271–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis5.7%–
CWE-Bench (AA)Artificial Analysis63.3%–
DeepSec-Bench (AA)Artificial Analysis26.2%–
CyberGym end-to-end (AA)Artificial Analysis78.6%–
MKA (AA)Artificial Analysis37.3%–
Maths
OTIS Mock AIMEEpoch AI Benchmarking Hub–91.1%
ProofBenchVals AI70.0%–
Arena MathsArena (LMArena)14841471
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–52.0%
LiveBench 2.0 Data AnalysisLiveBench72.3%†–
LiveBench ResearchLiveBench84.8%†–
AA-Omniscience v1.1Artificial Analysis-4.5–
CorpFinVals AI–66.5%
CaseLaw v2Vals AI–47.9%
Excel Modeling BenchmarkVals AI62.9%–
Excel Modeling Benchmark v1.1Vals AI67.3%–
MedCodeVals AI45.0%–
MedScribeVals AI88.3%–
Public Benefits Bench v1.1Vals AI68.9%–
Access to Justice BenchmarkVals AI70.0%–
Financial Coaching BenchVals AI75.4%–
Immigration BenchVals AI67.5%–
AA-Omniscience v1.1: accuracyArtificial Analysis34.8%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis39.8%–
Instruction following
IFBenchArtificial Analysis–76.6%
Arena Instruction FollowingArena (LMArena)14721451
Human preference
Arena TextArena (LMArena)14801460
Arena Creative WritingArena (LMArena)14481438
Arena Multi-turnArena (LMArena)14621466
Arena Longer QueriesArena (LMArena)14961473
Multimodal
Arena VisionArena (LMArena)1266–
LiveBench DesignLiveBench74.3%†–
SAGEVals AI84.5%–
Humanity's Sixth SenseScale AI SEAL25.2%†–
VIALS-AAHandshake AI43.5%–
Code2Video-AAArtificial Analysis1052–
AA-3DArtificial Analysis983–
Long context
AA-LCR v1.1Artificial Analysis86.3%80.7%
MLCRArtificial Analysis12.8%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–149.8
LiveBench 2.0LiveBench66.1%†–
AA Intelligence Index v5.0.1Artificial Analysis29.9–
AA Intelligence Index v4.3.2Artificial Analysis46.328.4
AA Progress Index v1Artificial Analysis321.2297.1
Vals IndexVals AI57.8–
Vals Finance IndexVals AI57.9%–
Vals Router IndexVals AI57.8%–
Vals Legal IndexVals AI72.1%–
AA Cyber IndexArtificial Analysis56.1–
Metadata
AA Openness IndexArtificial Analysis52.8–

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

  • MiMo-V2.6-Pro: 1 score revision.
  • MiMo-V2.6-Pro: 1 score revision.
  • Qwen3.6 Max (max): BenchLeader Index 62.8 → 62.3.
  • MiMo-V2.6-Pro: 6 score revisions.
  • MiMo-V2.6-Pro: 1 score revision.
  • MiMo-V2.6-Pro: 1 score revision.
  • MiMo-V2.6-Pro: BenchLeader Index 61.1 → 57.2.
  • MiMo-V2.6-Pro: 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; MiMo-V2.6-Pro cost per task moved from $0.13/M to $0.26/M (93% up).
  • Qwen3.6 Max (max): 1 new result (AA Progress Index v1).
  • MiMo-V2.6-Pro: BenchLeader Index 61.7 → 61.1.

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

MiMo-V2.6-Pro vs Qwen3.6 Max: questions

Is Qwen3.6 Max better than MiMo-V2.6-Pro?
Qwen3.6 Max (max) leads on quality: 62.1 vs 57.5. The BenchLeader Index combines every independent quality benchmark; Qwen3.6 Max (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
MiMo-V2.6-Pro vs Qwen3.6 Max: which is cheaper, and will that change?
MiMo-V2.6-Pro is cheaper today: $0.544 against $2.92 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is MiMo-V2.6-Pro or Qwen3.6 Max better for coding?
MiMo-V2.6-Pro scores higher in coding (59 vs 56 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1625 for MiMo-V2.6-Pro against 1482 for Qwen3.6 Max.
Is MiMo-V2.6-Pro or Qwen3.6 Max better for agents and tool use?
Qwen3.6 Max scores higher in agentic tasks (72 vs 57 on the category index, where 50 is average).
Which is better for long documents?
MiMo-V2.6-Pro scores higher on long-context benchmarks (68 vs 65). MiMo-V2.6-Pro accepts more context: 1,048,576 against 262,144 tokens for Qwen3.6 Max.
More questions (2)
Do independent benchmarks agree on MiMo-V2.6-Pro vs Qwen3.6 Max?
Across the 13 benchmarks both have, MiMo-V2.6-Pro leads 12, Qwen3.6 Max leads 1. Independent sources split: MiMo-V2.6-Pro leads on Arena Text; Qwen3.6 Max leads on BenchLeader Index.
When was MiMo-V2.6-Pro released?
MiMo-V2.6-Pro was released on 21 Sep 2026.