Skip to main content
BenchLM
Advertise

Model comparison

MiMo-V2-Flash vs Qwen3.5 397B

Data verified

Head-to-head evidence from 18 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

54.06/100
Margin
2.9pts
winning →
57.01/100
2 category wins0 category wins

Public leaderboard positions: MiMo-V2-Flash #91 (Supported); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiMo-V2-Flash and Qwen3.5 397B share 18 comparable benchmark results. 2 of 8 categories are comparable. 1 result is unique to MiMo-V2-Flash; 37 to Qwen3.5 397B.

Updated July 22, 2026
Shared results
18
MiMo-V2-Flash only
1
Qwen3.5 397B only
37
Comparable categories
2 / 8

Pick Qwen3.5 397B if you want the stronger benchmark profile. MiMo-V2-Flash only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 5 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.5 397B has the cleaner BenchAlign overall profile here, landing at 57.01 versus 54.06. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Qwen3.5 397B is also the more expensive model on tokens at $0.60 input / $3.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for MiMo-V2-Flash. That is roughly Infinityx on output cost alone. MiMo-V2-Flash is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiMo-V2-Flash gives you the larger context window at 256K, compared with 128K for Qwen3.5 397B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for MiMo-V2-Flash and Qwen3.5 397B
CategoryMiMo-V2-FlashΔQwen3.5 397B
KnowledgeMiMo-V2-Flash84.7Margin← 28.1Qwen3.5 397B56.6
CodingMiMo-V2-Flash73.4Margin← 6.9Qwen3.5 397B66.5
AgenticMiMo-V2-FlashNot measuredMarginNo overlapQwen3.5 397B56.5
ReasoningMiMo-V2-FlashNot measuredMarginNo overlapQwen3.5 397B63.2
MathMiMo-V2-FlashNot measuredMarginNo overlapQwen3.5 397B90.6
MultilingualMiMo-V2-FlashNot measuredMarginNo overlapQwen3.5 397B84.7
MultimodalMiMo-V2-FlashNot measuredMarginNo overlapQwen3.5 397B79.6
Inst. FollowingMiMo-V2-FlashNot measuredMarginNo overlapQwen3.5 397B92.6

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · MiMo-V2-FlashB · Qwen3.5 397B

  1. GPQA

    Knowledge
    Source ↗
    A 83.7%B 88.4%
    Winner: Qwen3.5 397BΔ 4.7
    GPQA: MiMo-V2-Flash scored 83.7%; Qwen3.5 397B scored 88.4%. Qwen3.5 397B wins this benchmark.

  2. MMLU-Pro

    Knowledge
    Source ↗
    A 84.9%B 87.8%
    Winner: Qwen3.5 397BΔ 2.9
    MMLU-Pro: MiMo-V2-Flash scored 84.9%; Qwen3.5 397B scored 87.8%. Qwen3.5 397B wins this benchmark.

  3. SWE-bench Verified

    Coding
    Source ↗
    A 73.4%B 76.2%
    Winner: Qwen3.5 397BΔ 2.8
    SWE-bench Verified: MiMo-V2-Flash scored 73.4%; Qwen3.5 397B scored 76.2%. Qwen3.5 397B wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricMiMo-V2-FlashQwen3.5 397BComparison
Input / output priceUSD per 1M tokensMiMo-V2-Flash$0 input / $0 outputQwen3.5 397B$0.6 input / $3.6 outputMiMo-V2-Flash has the lower combined listed price.
Generation speedtokens per secondMiMo-V2-Flash129 tok/sQwen3.5 397B96 tok/sMiMo-V2-Flash has the higher measured throughput.
First-answer latencyseconds to first tokenMiMo-V2-Flash2.14 sQwen3.5 397B2.44 sMiMo-V2-Flash reaches the first token sooner.
Context windowmaximum listed tokensMiMo-V2-Flash256KQwen3.5 397B128KMiMo-V2-Flash lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
AA Agentic IndexSource 12.0%19.9%Qwen3.5 397B leads
τ²-bench resultsSource 83.9%95.6%Qwen3.5 397B leads
GDPval-AASource 16.7%23.1%Qwen3.5 397B leads
GDPval-AASource 833962Qwen3.5 397B leads
Terminal-Bench 2.0Source —52.5%Not comparable
BrowseCompSource —62%Not comparable
Claw-EvalSource —56.8%Not comparable
QwenClawBenchSource —51.8%Not comparable
τ³-bench resultsSource —68.4%Not comparable
VITA-BenchSource —43.7%Not comparable
DeepPlanningSource —37.6%Not comparable
ToolathlonSource —36.3%Not comparable
MCP AtlasSource —46.1%Not comparable
MCP-TasksSource —74.2%Not comparable
WideResearchSource —74.0%Not comparable
Gert LabsSource —46.76%Not comparable
ResearchClawBenchSource —14.2%Not comparable
APEX-Agents-AASource —15.3%Not comparable
CodingMiMo-V2-Flash wins
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
SWE-bench VerifiedSource 73.4%76.2%Qwen3.5 397B leads
AA Coding IndexSource 49.8%48.2%MiMo-V2-Flash leads
AA-SciCodeSource 25.9%42.0%Qwen3.5 397B leads
LiveCodeBench v6Source —83.6%Not comparable
SWE-bench ProSource —50.9%Not comparable
Reasoning
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
AA-LCRSource 31.3%65.7%Qwen3.5 397B leads
CritPtSource 0.0%1.7%Qwen3.5 397B leads
LongBench v2Source —63.2%Not comparable
AI-NeedleSource —68.7%Not comparable
KnowledgeMiMo-V2-Flash wins
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
GPQASource 83.7%88.4%Qwen3.5 397B leads
MMLU-ProSource 84.9%87.8%Qwen3.5 397B leads
Artificial Analysis Intelligence IndexSource 24.7%33.7%Qwen3.5 397B leads
AA-GPQA DiamondSource 65.6%89.3%Qwen3.5 397B leads
AA-HLESource 8.0%27.3%Qwen3.5 397B leads
AA-Omniscience IndexSource -48.5%-29.8%Qwen3.5 397B leads
AA-Omniscience AccuracySource 15.2%31.4%Qwen3.5 397B leads
AA-Omniscience Hallucination RateSource 75.1%89.1%MiMo-V2-Flash leads
SuperGPQASource —70.4%Not comparable
MMLU-ReduxSource —94.9%Not comparable
C-EvalSource —93%Not comparable
HLESource —28.7%Not comparable
Math
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
AIME 2025Source 94.1%—Not comparable
AIME26Source —93.3%Not comparable
HMMT Feb 2025Source —94.8%Not comparable
HMMT Nov 2025Source —92.7%Not comparable
HMMT Feb 2026Source —87.9%Not comparable
MMAnswerBenchSource —80.9%Not comparable
Multilingual
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
MMLU-ProXSource —84.7%Not comparable
NOVA-63Source —59.1%Not comparable
Multimodal
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
MMMU-ProSource —79%Not comparable
MathVisionSource —88.6%Not comparable
CharXivSource —80.8%Not comparable
VideoMMMUSource —84.7%Not comparable
ScreenSpot ProSource —65.6%Not comparable
V*Source —95.8%Not comparable
AA-MMMU-ProSource —77.3%Not comparable
Inst. Following
BenchmarkMiMo-V2-FlashQwen3.5 397BResult
AA-IFBenchSource 39.9%78.8%Qwen3.5 397B leads
IFEvalSource —92.6%Not comparable
Frequently Asked Questions (3)

Which is better, MiMo-V2-Flash or Qwen3.5 397B?

Qwen3.5 397B is ahead on BenchLM's BenchAlign leaderboard, 57.01 to 54.06. The biggest single separator in this matchup is GPQA, where the scores are 83.7% and 88.4%.

Which is better for knowledge tasks, MiMo-V2-Flash or Qwen3.5 397B?

MiMo-V2-Flash has the edge for knowledge tasks in this comparison, averaging 84.7 versus 56.6. Inside this category, AA-GPQA Diamond is the benchmark that creates the most daylight between them.

Which is better for coding, MiMo-V2-Flash or Qwen3.5 397B?

MiMo-V2-Flash has the edge for coding in this comparison, averaging 73.4 versus 66.5. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Xiaomi Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 22, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.