BenchLeader

MiniMax M3.1 Flash vs Qwen3.5-122B-A10B

Full profiles: MiniMax M3.1 Flash (MiniMax) and Qwen3.5-122B-A10B (Alibaba): every benchmark, price and rank.

Updated · Data from 7 sources

As of 16 Nov 2026, MiniMax M3.1 Flash and Qwen3.5-122B-A10B are neck and neck on quality (54.3 vs 54.1 on the BenchLeader Index, inside the ±7.6 margin), and MiniMax M3.1 Flash is 4.2× cheaper at $0.262 vs $1.10 per 1M tokens blended. Choose MiniMax M3.1 Flash for coding (55 vs 45) and multimodal (62 vs 57), where it also streams ~1.5× faster; choose Qwen3.5-122B-A10B for fast first answers (1.1 s vs 43.3 s) and reasoning (59 vs 50).

Key facts (as of 16 Nov 2026)

  • MiniMax M3.1 Flash scores 54.3 on the BenchLeader Index and Qwen3.5-122B-A10B scores 54.1 (BenchLeader, 16 Nov 2026).
  • MiniMax M3.1 Flash costs $0.262 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.5-122B-A10B costs $1.10 per 1M tokens blended (list price, 16 Nov 2026).
  • MiniMax M3.1 Flash streams ~1.5× faster than Qwen3.5-122B-A10B (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 1 benchmarks both models have, MiniMax M3.1 Flash leads 1 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, MiniMax M3.1 Flash is rated 1584 and Qwen3.5-122B-A10B 1360 (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 45 category score; Arena WebDev 1584 vs 1360High
ReasoningQwen3.5-122B-A10B59 vs 50 category scoreHigh
Images and other mediaMiniMax M3.1 Flash62 vs 57 category scoreMedium
Chat quality (human preference)–Only Qwen3.5-122B-A10B has an Arena rating (59 category score)Not comparable
Lowest costMiniMax M3.1 Flash$0.262 vs $1.10 per 1M blended; agentic coding session $0.011 vs $0.037–
Fastest first answerQwen3.5-122B-A10B1.1 s (Qwen3.5-122B-A10B) 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

  • MiniMax M3.1 Flash and Qwen3.5-122B-A10B are neck and neck on quality (54.3 vs 54.1, within the ±7.6 margin).
  • MiniMax M3.1 Flash is stronger in coding, multimodal.
  • Qwen3.5-122B-A10B is stronger in reasoning.
  • MiniMax M3.1 Flash is 4.2× cheaper ($0.262 vs $1.10 per 1M blended).
  • MiniMax M3.1 Flash streams 1.6× faster (151 vs 92 tokens per second).

At a glance

SpecMiniMax M3.1 FlashQwen3.5-122B-A10B
DeveloperMiniMaxAlibaba
Released19 Oct 202624 Feb 2026
Context window (tokens)1,000,000262,144
Compared atMiniMax M3.1 FlashQwen3.5-122B-A10B
Open weightsYesYes
Price in / out / cached input per 1M$0.150 / $0.600 / $0.015$0.400 / $3.20 / –

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.

CategoryMiniMax M3.1 FlashQwen3.5-122B-A10BLeader
Reasoning50.158.9Qwen3.5-122B-A10B
Coding55.445.2MiniMax M3.1 Flash
Agents & tools55.2–not comparable
Maths–60.1not comparable
Knowledge45.9–not comparable
Human preference–59.2not comparable
Multimodal61.557.4MiniMax M3.1 Flash
Long context64.5–not 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 avg75ReasoningCodingMultimodalMiniMax M3.1 Flash, Reasoning: 50.1MiniMax M3.1 Flash, Coding: 55.4MiniMax M3.1 Flash, Multimodal: 61.5Qwen3.5-122B-A10B, Reasoning: 58.9Qwen3.5-122B-A10B, Coding: 45.2Qwen3.5-122B-A10B, Multimodal: 57.4

Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Knowledge, Instruction following, Long context, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 1 benchmarks both have, MiniMax M3.1 Flash leads 1, Qwen3.5-122B-A10B leads 0.

Overall indexMiniMax M3.1 FlashQwen3.5-122B-A10BLeader
BenchLeader Index54.354.1neck 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.

MeasureMiniMax M3.1 FlashQwen3.5-122B-A10B
Blended price per 1M tokens$0.262$1.10
Input / output per 1M$0.150 / $0.600$0.400 / $3.20
Cached input per 1M$0.015–
Price per task: chat reply$0.0002$0.0011
Price per task: summarize a 30-page report$0.0022$0.0067
Price per task: code edit$0.0018$0.0072
Price per task: agentic coding session$0.011$0.037
Price per task: structured extraction$0.0004$0.0014
Agentic coding session, input mostly cached$0.0053–
Cost per benchmark task (AA Index)$0.491–
Output tokens per task (AA Index)138k–
Of which reasoning103k–
Time per task (AA Index)15 min–
Output speed151 tok/s92 tok/s
Time to first answer43.3 s1.1 s
Time to a complete answer, last measured 13 Nov 2026141.5 s–

Each model is compared at its best-ranked reasoning-effort setting. MiniMax M3.1 Flash scores 54.3 and takes 43 s to its first answer token. Qwen3.5-122B-A10B scores 54.1 and takes 1 s to its first answer token; Qwen3.5-122B-A10B (thinking) scores 53.9 in 18 s, Qwen3.5-122B-A10B (no reasoning) scores 48.4 in 4 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

82 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.

MetricPublisherMiniMax M3.1 FlashQwen3.5-122B-A10B
BenchLeader IndexBenchLeader54.354.1
Agents & tools scoreBenchLeader55.2–
Coding scoreBenchLeader55.445.2
Knowledge scoreBenchLeader45.9–
Long context scoreBenchLeader64.5–
Multimodal scoreBenchLeader61.557.4
Reasoning scoreBenchLeader50.158.9
Human preference scoreBenchLeader–59.2
Maths scoreBenchLeader–60.1
Blended price $/MBenchLeader$0.262$1.10
Output speedBenchLeader151 tok/s92 tok/s
Time to first answerBenchLeader43.3 s1.1 s
Context windowBenchLeader1,000,000 tokens262,144 tokens
Reasoning
Arena Hard PromptsArena (LMArena)–1433
LiveBench 2.0 ReasoningLiveBench82.9%†–
GPQA Diamond (AA)Artificial Analysis–85.7%†
Humanity's Last Exam (AA)Artificial Analysis48.0%25.2%†
HLE-Diamond (AA)Artificial Analysis28.1%7.3%†
CritPtArtificial Analysis22.3%0.6%†
CritPt v2 hard subset (AA)Artificial Analysis32.5%–
Arena ExpertArena (LMArena)–1441
Mystery Game PuzzlesEpoch AI Benchmarking Hub–17.0%†
LMCAEpoch AI Benchmarking Hub–32.2%†
DTBenchEpoch AI Benchmarking Hub–84.3%†
Coding
SciCodeSciCode–35.6%†
Arena CodingArena (LMArena)–1458
Arena WebDevArena (LMArena)15841360
LiveBench 2.0 CodingLiveBench68.8%†–
SciCode (AA)Artificial Analysis53.4%39.7%†
Vibe Code Bench v1.1Vals AI73.9%†–
Vibe Code Bench 1-100 v1.1Vals AI19.8%†–
SWE-Bench Pro V2Scale AI SEAL96.6%†–
SWE-Bench Pro V2 HARDScale AI SEAL84.3%†–
Terminal-Bench 4.0 (AA)Artificial Analysis25.8%0.0%†
Terminal-Bench 2.1 (AA)Artificial Analysis–47.6%†
GameBench 2 by reasoning settingDuelLab GameBench 230.3†–
Design Arena WebsiteDesign Arena1277–
FrontierCode 1.1 (AA)Artificial Analysis38.6%–
Show all 82 benchmarks
MetricPublisherMiniMax M3.1 FlashQwen3.5-122B-A10B
Coding
FrontierCode 2.0 (AA)Artificial Analysis20.8%–
Agents & tools
Arena AgentArena (LMArena)-2.7–
LiveBench Long AgenticLiveBench25.7%†–
LiveBench BrowserLiveBench80.6%†–
Terminal-Bench HardArtificial Analysis–31.1%†
τ²-Bench Telecom (AA)Artificial Analysis–93.6%†
HiL-BenchScale AI SEAL65.7%–
GDPval-AA v2.1, normalised scoreArtificial Analysis47.9%15.7%†
GDPval-AA v2.1Artificial Analysis1465821†
τ³-Banking (AA)Artificial Analysis–15.3%†
Finance Agent v2.1Vals AI58.8%†–
Harvey's Legal Agent Benchmark v1.1Vals AI7.5%†–
Legal Research BenchVals AI34.1%†–
Tax Agent BenchVals AI32.1%†–
Terminal-Bench 4.0 (Vals)Vals AI25.3%†–
Arena Agent Task CompletionArena (LMArena)-0.7–
AutomationBenchArtificial Analysis72.5%5.5%†
GDP.pdf (AA)Artificial Analysis20.8%3.4%†
AA-Briefcase v1.1Artificial Analysis1474499†
GDPxGDPx by SemiAnalysis4.0%†–
Design Arena AgenticDesign Arena1252–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis3.3%–
MKA (AA)Artificial Analysis33.5%–
Maths
Arena MathsArena (LMArena)–1425
Knowledge
LiveBench 2.0 Data AnalysisLiveBench71.4%†–
LiveBench ResearchLiveBench76.7%†–
AA-Omniscience v1.1Artificial Analysis-6.4–
PRBench FinanceScale AI SEAL45.6%–
PRBench LegalScale AI SEAL45.1%–
Excel Modeling Benchmark v1.1Vals AI67.8%†–
Access to Justice BenchmarkVals AI73.3%†–
AA-Omniscience v1.1: accuracyArtificial Analysis45.1%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis6.3%–
Global-MMLU-Lite (AA)Artificial Analysis–89.1%†
Instruction following
IFBenchArtificial Analysis–75.7%†
Arena Instruction FollowingArena (LMArena)–1406
Human preference
Arena TextArena (LMArena)–1416
Arena Creative WritingArena (LMArena)–1365
Arena Multi-turnArena (LMArena)–1419
Arena Longer QueriesArena (LMArena)–1418
Multimodal
Arena VisionArena (LMArena)–1244
LiveBench DesignLiveBench71.2%†–
MMMU-ProArtificial Analysis79.1%75.0%†
SAGEVals AI85.3%†–
VIALS-AAHandshake AI29.8%–
Long context
AA-LCR v1.1Artificial Analysis79.7%76.3%†
MLCRArtificial Analysis16.7%7.8%†
Composite
LiveBench 2.0LiveBench63.7%†–
AA Intelligence Index v5.0.1Artificial Analysis29.1–
AA Intelligence Index v4.3.2Artificial Analysis42.715.6†
AA Progress Index v1Artificial Analysis317.6261.5†
Vals IndexVals AI53.8†–
Vals Finance IndexVals AI55.9%†–
Vals Router IndexVals AI53.8%–
Vals Legal IndexVals AI67.1%†–
Safety & honesty
FORTRESSScale AI SEAL52.1%–
Metadata
AA Openness IndexArtificial Analysis27.838.9†

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

  • MiniMax M3.1 Flash: BenchLeader Index 53.7 → 54.3.
  • 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.
  • MiniMax M3.1 Flash: 2 new results (PRBench Finance, PRBench Legal).
  • MiniMax M3.1 Flash: 1 score revision.
  • MiniMax M3.1 Flash: 1 score revision.

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

MiniMax M3.1 Flash vs Qwen3.5-122B-A10B: questions

Is MiniMax M3.1 Flash better than Qwen3.5-122B-A10B?
MiniMax M3.1 Flash and Qwen3.5-122B-A10B are neck and neck on quality (54.3 vs 54.1, within the ±7.6 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.
MiniMax M3.1 Flash vs Qwen3.5-122B-A10B: which is cheaper, and will that change?
MiniMax M3.1 Flash is cheaper today: $0.262 against $1.10 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is MiniMax M3.1 Flash or Qwen3.5-122B-A10B better for coding?
MiniMax M3.1 Flash scores higher in coding (55 vs 45 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1584 for MiniMax M3.1 Flash against 1360 for Qwen3.5-122B-A10B.
Which is faster, MiniMax M3.1 Flash or Qwen3.5-122B-A10B?
MiniMax M3.1 Flash streams ~1.5× faster (151 vs 92 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
MiniMax M3.1 Flash accepts more context: 1,000,000 against 262,144 tokens for Qwen3.5-122B-A10B.
More questions (3)
Which has lower latency?
Qwen3.5-122B-A10B answers first: 1.1 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 MiniMax M3.1 Flash vs Qwen3.5-122B-A10B?
Across the 1 benchmarks both have, MiniMax M3.1 Flash leads 1, Qwen3.5-122B-A10B leads 0.
When was MiniMax M3.1 Flash released?
MiniMax M3.1 Flash was released on 19 Oct 2026.