BenchLeader

MiMo-V2.5-Pro vs Qwen3.8 Max

Full profiles: MiMo-V2.5-Pro (Xiaomi) and Qwen3.8 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 14 sources

As of 16 Nov 2026, MiMo-V2.5-Pro and Qwen3.8 Max are neck and neck on quality (55.5 vs 58.7 on the BenchLeader Index, inside the ±5.3 margin), and MiMo-V2.5-Pro is 2.0× cheaper at $1.50 vs $3.00 per 1M tokens blended. Choose MiMo-V2.5-Pro for reasoning (66 vs 52) and fast first answers (2.8 s vs 119.6 s); choose Qwen3.8 Max for agents & tools (59 vs 46), maths (65 vs 58), and human preference (68 vs 60).

Key facts (as of 16 Nov 2026)

  • MiMo-V2.5-Pro scores 55.5 on the BenchLeader Index and Qwen3.8 Max scores 58.7 (BenchLeader, 16 Nov 2026).
  • MiMo-V2.5-Pro costs $1.50 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.8 Max costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 30 benchmarks both models have, Qwen3.8 Max leads 30 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, MiMo-V2.5-Pro is rated 1479 and Qwen3.8 Max 1676 (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
CodingQwen3.8 Max62 vs 56 category score; Arena WebDev 1676 vs 1479Medium
Agents & tool useQwen3.8 Max59 vs 46 category score; Terminal-Bench 2.1 (Vals) 67.4% vs 57.3%High
MathsQwen3.8 Max65 vs 58 category score; Arena Maths 1505 vs 1479High
ReasoningMiMo-V2.5-Pro66 vs 52 category score; Arena Hard Prompts 1494 vs 1507High
KnowledgeQwen3.8 Max58 vs 55 category score; MMLU-Pro 88.6% vs 84.6%Medium
Chat quality (human preference)Qwen3.8 Max68 vs 60 on Arena votesMedium
Lowest costMiMo-V2.5-Pro$1.50 vs $3.00 per 1M blended; agentic coding session $0.072 vs $0.144–
Fastest first answerMiMo-V2.5-Pro2.8 s (MiMo-V2.5-Pro) vs 119.6 s (Qwen3.8 Max (max)) 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

  • MiMo-V2.5-Pro and Qwen3.8 Max (max) are neck and neck on quality (55.5 vs 58.7, within the ±5.3 margin).
  • MiMo-V2.5-Pro is stronger in reasoning.
  • Qwen3.8 Max (max) is stronger in agents & tools, coding, human preference, knowledge, maths.
  • MiMo-V2.5-Pro is 2.0× cheaper ($1.50 vs $3.00 per 1M blended).

At a glance

SpecMiMo-V2.5-ProQwen3.8 Max
DeveloperXiaomiAlibaba
Released23 Apr 20263 Aug 2026
Context window (tokens)1,048,5761,000,000
Compared atMiMo-V2.5-ProQwen3.8 Max (max)
Open weightsYesNo
Price in / out / cached input per 1M$1.00 / $3.00 / $0.0043$2.00 / $6.00 / $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.

CategoryMiMo-V2.5-ProQwen3.8 Max (max)Leader
Reasoning65.851.5MiMo-V2.5-Pro
Coding56.261.6Qwen3.8 Max
Agents & tools46.058.5Qwen3.8 Max
Maths57.665.2Qwen3.8 Max
Knowledge54.558.0Qwen3.8 Max
Human preference60.167.5Qwen3.8 Max
Multimodal–65.7not comparable
Long context–64.8not comparable
Composite–45.0not 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 & toolsMathsKnowledgeHumanpreferenceMiMo-V2.5-Pro, Reasoning: 65.8MiMo-V2.5-Pro, Coding: 56.2MiMo-V2.5-Pro, Agents & tools: 46.0MiMo-V2.5-Pro, Maths: 57.6MiMo-V2.5-Pro, Knowledge: 54.5MiMo-V2.5-Pro, Human preference: 60.1Qwen3.8 Max, Reasoning: 51.5Qwen3.8 Max, Coding: 61.6Qwen3.8 Max, Agents & tools: 58.5Qwen3.8 Max, Maths: 65.2Qwen3.8 Max, Knowledge: 58.0Qwen3.8 Max, Human preference: 67.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 30 benchmarks both have, MiMo-V2.5-Pro leads 0, Qwen3.8 Max leads 30. Every overall index that rates both puts Qwen3.8 Max ahead.

Overall indexMiMo-V2.5-ProQwen3.8 Max (max)Leader
BenchLeader Index55.558.7neck and neck
Arena Text14661484Qwen3.8 Max

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-V2.5-ProQwen3.8 Max (max)
Blended price per 1M tokens$1.50$3.00
Input / output per 1M$1.00 / $3.00$2.00 / $6.00
Cached input per 1M$0.0043$0.250
Price per task: chat reply$0.0013$0.0026
Price per task: summarize a 30-page report$0.014$0.028
Price per task: code edit$0.011$0.021
Price per task: agentic coding session$0.072$0.144
Price per task: structured extraction$0.0026$0.0052
Agentic coding session, input mostly cached$0.027$0.065
Cost per benchmark task (AA Index)–$10.02
Output tokens per task (AA Index)–171k
Of which reasoning–120k
Time per task (AA Index)–48 min
Output speed68 tok/s59 tok/s
Time to first answer2.8 s119.6 s
Time to a complete answer, last measured 13 Nov 2026–294.1 s

Each model is compared at its best-ranked reasoning-effort setting. MiMo-V2.5-Pro scores 55.5 and takes 3 s to its first answer token. Qwen3.8 Max (max) scores 58.7 and takes 120 s to its first answer token; Qwen3.8 Max (xhigh) scores 56.6 in 3 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

143 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-V2.5-ProQwen3.8 Max (max)
BenchLeader IndexBenchLeader55.558.7
Agents & tools scoreBenchLeader46.058.5
Coding scoreBenchLeader56.261.6
Human preference scoreBenchLeader60.167.5
Knowledge scoreBenchLeader54.558.0
Maths scoreBenchLeader57.665.2
Reasoning scoreBenchLeader65.851.5
Composite scoreBenchLeader–45.0
Long context scoreBenchLeader–64.8
Multimodal scoreBenchLeader–65.7
Blended price $/MBenchLeader$1.50$3.00
Output speedBenchLeader68 tok/s59 tok/s
Time to first answerBenchLeader2.8 s119.6 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–92.7%†
Arena Hard PromptsArena (LMArena)14941507
LiveBench 2.0 ReasoningLiveBench–88.2%
LiveBench 1.0 ReasoningLiveBench–88.2%
GPQA Diamond (AA)Artificial Analysis76.2%†92.8%
Humanity's Last Exam (AA)Artificial Analysis14.8%†43.1%
HLE-Diamond (AA)Artificial Analysis–24.0%
GPQA Diamond (Vals)Vals AI82.6%93.7%
CritPtArtificial Analysis1.1%†20.0%
CritPt v2 hard subset (AA)Artificial Analysis–29.5%
MysteryMechanismVals AI–23.9%
Arena ExpertArena (LMArena)15071514
Chess PuzzlesEpoch AI Benchmarking Hub–46.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub–38.0%†
LMCAEpoch AI Benchmarking Hub29.5%46.2%†
DTBenchEpoch AI Benchmarking Hub84.5%92.0%†
Coding
SciCodeSciCode50.2%53.2%
Arena CodingArena (LMArena)15201523
Arena WebDevArena (LMArena)14791676
LiveBench 2.0 CodingLiveBench–60.9%
LiveBench 1.0 CodingLiveBench–72.9%
SciCode (AA)Artificial Analysis50.6%†53.2%
LiveCodeBenchVals AI81.3%87.8%
IOIVals AI–68.9%
SWE-bench (Vals)Vals AI74.0%85.6%
Show all 143 benchmarks
MetricPublisherMiMo-V2.5-ProQwen3.8 Max (max)
Coding
Code MigrationVals AI21.6%24.0%
ProgramBenchVals AI–0.0%
SWE-bench MultimodalVals AI–42.5%
Vibe Code Bench 1-100Vals AI–12.8%
Vibe Code Bench v1.1Vals AI34.1%64.7%
SWE Atlas v1.1Scale AI SEAL–64.4%
SWE Atlas v1.1: Codebase QnAScale AI SEAL–81.5%
SWE Atlas v1.1: Test WritingScale AI SEAL–58.9%
SWE Atlas v1.1: RefactoringScale AI SEAL–52.9%
MirrorCodeEpoch AI Benchmarking Hub–52.2%†
DeepSWE v1.1Epoch AI Benchmarking Hub–57.5%†
ALE-BenchEpoch AI Benchmarking Hub899.81679.1†
FrontierSWEEpoch AI Benchmarking Hub–17.8%†
Terminal-Bench 4.0 (AA)Artificial Analysis0.0%†38.9%
Terminal-Bench 2.1 (AA)Artificial Analysis65.2%†88.8%
Startrise FrontendStartrise–71.3%
GameBench 2 OverallDuelLab GameBench 2–54.2†
GameBench 2 by reasoning settingDuelLab GameBench 227.4†69.6†
Design Arena WebsiteDesign Arena12621269
FrontierCode 1.1 (AA)Artificial Analysis–43.2%
FrontierCode 2.0 (AA)Artificial Analysis–23.4%
Agents & tools
Terminal-BenchTerminal-Bench–27.0%
APEX-AgentsMercor–63.3%
Arena AgentArena (LMArena)–0.1
LiveBench Long AgenticLiveBench–26.6%
LiveBench BrowserLiveBench–49.4%
LiveBench Agentic CodingLiveBench–64.7%
Terminal-Bench HardArtificial Analysis35.6%†–
τ²-Bench Telecom (AA)Artificial Analysis72.5%†–
Terminal-Bench 2.1 (Vals)Vals AI57.3%67.4%
τ³-bench Bankingτ²-bench–55.1%†
GDPval-AA v2.1, normalised scoreArtificial Analysis–58.3%
GDPval-AA v2.1Artificial Analysis1128†1674
τ³-Banking (AA)Artificial Analysis9.9%†51.3%
ITBench SRE (AA)Artificial Analysis38.2%†40.3%
Analyst Agent (AA)Artificial Analysis20.0%†45.0%
APEX-Agents (AA)Artificial Analysis2.4%†42.4%
CyberBenchVals AI–28.6%
Finance Agent v2Vals AI41.5%50.6%
Harvey's Legal Agent Benchmark v1Vals AI2.1%10.4%
Legal Research BenchVals AI15.9%47.6%
SkillsBenchVals AI–42.0%
Tax Agent BenchVals AI11.5%32.1%
Terminal-Bench 4.0 (Vals)Vals AI0.5%34.3%
Terminal-Bench ScienceVals AI–12.9%
Arena SearchArena (LMArena)–1227
Arena Agent Task CompletionArena (LMArena)–4.5
AutomationBenchArtificial Analysis13.7%†56.2%
GDP.pdf (AA)Artificial Analysis4.0%†22.8%
EnterpriseOps-GymArtificial Analysis–47.6%
AA-Briefcase v1.1Artificial Analysis884†1604
GDPxGDPx by SemiAnalysis–3.5%
Design Arena AgenticDesign Arena–1264
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–11.9%
MKA (AA)Artificial Analysis–37.4%
FACTS SearchGoogle–85.0%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–74.7%†
FrontierMath Tier 4Epoch AI Benchmarking Hub–46.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub–100.0%†
ProofBenchVals AI22.0%58.0%
LiveBench MathematicsLiveBench–91.3%
Arena MathsArena (LMArena)14791505
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–47.3%†
LiveBench 2.0 Data AnalysisLiveBench–78.4%
LiveBench ResearchLiveBench–72.8%
LiveBench 1.0 Data AnalysisLiveBench–78.4%
AA-Omniscience v1.1Artificial Analysis–10.5
MMLU-ProVals AI84.6%88.6%
LegalBenchVals AI77.1%83.6%
CorpFinVals AI61.4%65.8%
TaxEvalVals AI73.8%75.5%
Excel Modeling BenchmarkVals AI55.2%60.1%
Excel Modeling Benchmark v1.1Vals AI–66.0%
MedCodeVals AI32.5%40.7%
MedScribeVals AI83.7%85.0%
Public Benefits Bench v1.1Vals AI–67.1%
Access to Justice BenchmarkVals AI–76.4%
Financial Coaching BenchVals AI–75.6%
Immigration BenchVals AI–70.1%
GDP.pdfEpoch AI Benchmarking Hub–23.2%†
AA-Omniscience v1.1: accuracyArtificial Analysis–29.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–72.9%
FACTS ParametricGoogle–30.8%
Instruction following
LiveBench LanguageLiveBench–79.7%
LiveBench Instruction FollowingLiveBench–74.1%
IFBenchArtificial Analysis42.7%†–
Arena Instruction FollowingArena (LMArena)14681478
Human preference
Arena TextArena (LMArena)14661484
EQ-Bench 4EQ-Bench1198–
EQ-Bench Creative Writing v3EQ-Bench1493–
Arena Creative WritingArena (LMArena)14331472
Arena Multi-turnArena (LMArena)14801495
Arena Longer QueriesArena (LMArena)14861496
Multimodal
Arena VisionArena (LMArena)–1312
LiveBench DesignLiveBench–76.6%
MMMU-ProArtificial Analysis–82.8%
MMMU-Pro (Vals)Vals AI–88.0%
MortgageTaxVals AI–64.0%
SAGEVals AI–81.8%
Humanity's Sixth SenseScale AI SEAL–33.0%
Furniture AssemblyEpoch AI Benchmarking Hub–20.0%†
VIALS-AAHandshake AI–31.7%
Code2Video-AAArtificial Analysis–1021
AA-3DArtificial Analysis–954
FACTS MultimodalGoogle–51.5%
Long context
AA-LCR v1.1Artificial Analysis41.7%†80.3%
MLCRArtificial Analysis5.6%†26.1%
FACTS GroundingGoogle–73.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–157.6
LiveBench 2.0LiveBench–60.9%
LiveBench 1.0LiveBench–78.5%
AA Intelligence Index v5.0.1Artificial Analysis–33.6
AA Intelligence Index v4.3.2Artificial Analysis18.3†45.4
AA Progress Index v1Artificial Analysis241†323.7
Vals RSI IndexVals AI–21.8%
Vals Multimodal IndexVals AI–65.4%
Safety & honesty
DistressBenchScale AI SEAL–77.6%
Metadata
AA Openness IndexArtificial Analysis38.9†–

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-V2.5-Pro: MiMo-V2.5-Pro cached input price moved from $0.20/M to $0.0043/M (98% down).
  • Qwen3.8 Max (max): 1 score revision.
  • Qwen3.8 Max (max): 1 score revision.
  • MiMo-V2.5-Pro: BenchLeader Index 55.0 → 55.6.
  • Qwen3.8 Max (max): 6 score revisions.
  • Qwen3.8 Max (max): 1 score revision.
  • Qwen3.8 Max (max): 1 new result (FACTS Search); 1 score revision.
  • Qwen3.8 Max (max): 1 score revision; cached input price moved from $0.22/M to $0.25/M (13% up).
  • Qwen3.8 Max (max): cached input price moved from $0.25/M to $0.22/M (11% down).
  • Qwen3.8 Max (max): 1 score revision; cached input price moved from $0.22/M to $0.25/M (13% up).

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

MiMo-V2.5-Pro vs Qwen3.8 Max: questions

Is MiMo-V2.5-Pro better than Qwen3.8 Max?
MiMo-V2.5-Pro and Qwen3.8 Max (max) are neck and neck on quality (55.5 vs 58.7, within the ±5.3 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.
MiMo-V2.5-Pro vs Qwen3.8 Max: which is cheaper, and will that change?
MiMo-V2.5-Pro is cheaper today: $1.50 against $3.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is MiMo-V2.5-Pro or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher in coding (62 vs 56 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1479 for MiMo-V2.5-Pro against 1676 for Qwen3.8 Max.
Which is faster, MiMo-V2.5-Pro or Qwen3.8 Max?
MiMo-V2.5-Pro streams faster (68 vs 59 output tokens per second, Artificial Analysis 7-day median).
Is MiMo-V2.5-Pro or Qwen3.8 Max better for agents and tool use?
Qwen3.8 Max scores higher in agentic tasks (59 vs 46 on the category index, where 50 is average). On Terminal-Bench 2.1 (Vals), the top shared agents & tools benchmark, it is 57.3% for MiMo-V2.5-Pro against 67.4% for Qwen3.8 Max.
More questions (4)
Which is better for long documents?
Both take about 1M tokens: MiMo-V2.5-Pro 1,048,576, Qwen3.8 Max 1,000,000.
Which has lower latency?
MiMo-V2.5-Pro answers first: 2.8 s against 119.6 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 MiMo-V2.5-Pro vs Qwen3.8 Max?
Across the 30 benchmarks both have, MiMo-V2.5-Pro leads 0, Qwen3.8 Max leads 30. Every overall index that rates both puts Qwen3.8 Max ahead.
When was Qwen3.8 Max released?
Qwen3.8 Max was released on 3 Aug 2026.