Qwen 3.8 27Bvs.MiMo-V2.5

Which one is better?

Qwen 3.8 27B is clearly ahead in the overall index. Qwen 3.8 27B is cheaper for input, MiMo-V2.5 for output.

IntelligenceOverall index, 0 to 100 · higher is better

Qwen 3.8 27B

Rank 44 to 57

MiMo-V2.5

Rank 60 to 69

SpeedTokens per second · higher is better

Qwen 3.8 27B

slow

MiMo-V2.5

fairly slow

PriceDollars per 1M tokens · lower is better

$0.66

Qwen 3.8 27B

fairly cheap

$0.18

MiMo-V2.5

cheap

Qwen 3.8 27B

Subscription: No Alibaba subscription includes this model. Through other providers from ≈ €1.06 a month (Command Code Go, with limited credits). 10 plans in Germany.
Via API: $0.04 input, $2.50 output per 1M tokens according to the provider; the price index has listed it at $0.42 and $3 since Oct 27, 2026.

MiMo-V2.5

Subscription: No Xiaomi subscription includes this model. Through other providers from ≈ €1.06 a month (Command Code Go, with limited credits). 10 plans in Germany.
Via API: $0.14 input, $0.28 output per 1M tokens, cheaper since Oct 26, 2026 (before $0.168 and $0.336).

Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT

Where is the difference?

Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.

Qwen 3.8 27B ahead: 7MiMo-V2.5 ahead: 0level: 2too little data: 1of 10 areas

AreaQwen 3.8 27BMiMo-V2.50 to 100, higher is betterResult

Areas in the overall index

CodingQwen 3.8 27B ahead135

Reasoninglevel62

MathematicsQwen 3.8 27B ahead84

KnowledgeQwen 3.8 27B ahead52

AgentsQwen 3.8 27B ahead213

Generalonly MiMo-V2.5 has a scorenot enough data4

MultimodalQwen 3.8 27B ahead134

Specialist fields

FinanceQwen 3.8 27B ahead343

LegalQwen 3.8 27B ahead23below 1

Healthlevel3below 1

Show 1 more areas that do not count toward the overall index

AreaQwen 3.8 27BMiMo-V2.50 to 100, higher is betterResult

Cybersecurityonly Qwen 3.8 27B has a score19not enough data

See for yourself: same task, one attempt

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Shared test round: 43b8c5c46830

Qwen 3.8 27B

MiMo-V2.5

API request failed. The model was not evaluated.

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Qwen 3.8 27B

Not tested yet

MiMo-V2.5

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

Current attempt

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: xiaomi/mimo-v2.5
API model reported in response: xiaomi/mimo-v2.5
Reasoning setting: high
Pinned endpoint: Xiaomi | xiaomi/mimo-v2.5-20260422
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 136.3 s

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Earlier attempts (3)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high
Sep 7, 2026API request failedReasoning setting: high

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

All data side by side

The better value is bold. For the overall index only when the gap is clear.

Metric	Qwen 3.8 27B	MiMo-V2.5
Intelligence
Overall index0 to 100, higher is better	11	2
Rank	Rank 44 to 57 of 95	Rank 60 to 69 of 95
Price per 1M tokens
Inputwhat you send	$0.04	$0.14
Outputwhat the model writes	$2.50	$0.28
Speed
Tokens per second	40	72
Technical
Context windowhow much text the model reads at once	262,144 tokens≈ 390 A4 pages	1 M tokens≈ 1,500 A4 pages
Knowledge cutoff	n/a	n/a
Released	Aug 14, 2026	Apr 23, 2026
Availability	Active	Open Source
Open weights	yes	yes

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: Qwen 3.8 27BB: MiMo-V2.5

Code MigrationOverall · higher is betterTest setup not documented as identical14.2%14.2%Vals AIAs of 10/18/2026

EMBOverall · higher is betterTest setup not documented as identical59.7%55.1%Vals AIAs of 10/20/2026

Finance Agent (v2)Overall · higher is betterTest setup not documented as identical48.6%36.7%Vals AIAs of 10/20/2026

GPQA DiamondOverall · higher is betterTest setup not documented as identical88.9%81.6%Vals AIAs of 09/01/2026

Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identical36.1%9.1%Vals AIAs of 10/26/2026

LegalBenchOverall · higher is betterTest setup not documented as identical82.4%78.9%Vals AIAs of 10/13/2026

LiveCodeBenchOverall · higher is betterTest setup not documented as identical84%81.5%Vals AIAs of 09/01/2026

MedCodeOverall · higher is betterTest setup not documented as identical28.7%31.9%Vals AIAs of 10/13/2026

MedScribeOverall · higher is betterTest setup not documented as identical83.8%72.2%Vals AIAs of 10/13/2026

MMLU ProOverall · higher is betterTest setup not documented as identical84.3%82.9%Vals AIAs of 09/01/2026

Show 54 more benchmarks

MMMU ProOverall · higher is betterTest setup not documented as identical83.9%80%Vals AIAs of 09/01/2026

MortgageTaxOverall · higher is betterTest setup not documented as identical64.9%59.3%Vals AIAs of 09/01/2026

ProofBench v1.1Overall · higher is betterTest setup not documented as identical16%16%Vals AIAs of 10/24/2026

SWE-bench VerifiedOverall · higher is betterTest setup not documented as identical86%71%Vals AIAs of 09/01/2026

Tax Agent BenchOverall · higher is betterTest setup not documented as identical30.9%7.8%Vals AIAs of 10/26/2026

TaxEval v2Overall · higher is betterTest setup not documented as identical70.9%71.8%Vals AIAs of 09/01/2026

Terminal-Bench 2.1Overall · higher is betterTest setup not documented as identical58.4%60.7%Vals AIAs of 10/01/2026

Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identical64.9%42.2%Vals AIAs of 10/26/2026

Code MigrationCLI · higher is betterTest setup not documented as identical2.2%9.9%Vals AIAs of 10/18/2026

EMBComps · higher is betterTest setup not documented as identical53.3%47.2%Vals AIAs of 10/20/2026

Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identical47.3%31.7%Vals AIAs of 10/20/2026

GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identical88.9%79.8%Vals AIAs of 09/01/2026

Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identical45.5%10.6%Vals AIAs of 10/26/2026

LegalBenchConclusion Tasks · higher is betterTest setup not documented as identical88.4%86.4%Vals AIAs of 10/13/2026

LiveCodeBenchEasy · higher is betterTest setup not documented as identical99.1%98.4%Vals AIAs of 09/01/2026

MMLU ProBiology · higher is betterTest setup not documented as identical91.5%90.2%Vals AIAs of 09/01/2026

MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identical69.4%61%Vals AIAs of 09/01/2026

SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identical90.2%80.9%Vals AIAs of 09/01/2026

Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identical6.7%0%Vals AIAs of 10/26/2026

TaxEval v2Correctness · higher is betterTest setup not documented as identical60.1%60.8%Vals AIAs of 09/01/2026

Terminal-Bench 2.1Easy · higher is betterTest setup not documented as identical50%100%Vals AIAs of 10/01/2026

Code MigrationCOBOL · higher is betterTest setup not documented as identical50%27.3%Vals AIAs of 10/18/2026

EMBDataroom · higher is betterTest setup not documented as identical79.7%75%Vals AIAs of 10/20/2026

Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identical36.8%23.8%Vals AIAs of 10/20/2026

GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identical88.9%83.3%Vals AIAs of 09/01/2026

Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identical88.5%71.9%Vals AIAs of 10/26/2026

LegalBenchInterpretation Tasks · higher is betterTest setup not documented as identical82%74.4%Vals AIAs of 10/13/2026

LiveCodeBenchHard · higher is betterTest setup not documented as identical65.7%59.1%Vals AIAs of 09/01/2026

MMLU ProBusiness · higher is betterTest setup not documented as identical90.2%89.2%Vals AIAs of 09/01/2026

MortgageTaxSemantic Extraction · higher is betterTest setup not documented as identical60.5%57.5%Vals AIAs of 09/01/2026

SWE-bench Verified>4 hours · higher is betterTest setup not documented as identical66.7%0%Vals AIAs of 09/01/2026

Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identical48.3%31.7%Vals AIAs of 10/26/2026

TaxEval v2Stepwise Reasoning · higher is betterTest setup not documented as identical81.6%82.9%Vals AIAs of 09/01/2026

Terminal-Bench 2.1Hard · higher is betterTest setup not documented as identical43.3%36.7%Vals AIAs of 10/01/2026

Code MigrationCode Quality · higher is betterTest setup not documented as identical4.197 / 52.788 / 5Vals AIAs of 10/18/2026

EMBDCF · higher is betterTest setup not documented as identical50%52.5%Vals AIAs of 10/20/2026

Finance Agent (v2)Comparables · higher is betterTest setup not documented as identical38.9%31.7%Vals AIAs of 10/20/2026

Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identical41.9%9.3%Vals AIAs of 10/26/2026

LegalBenchIssue Tasks · higher is betterTest setup not documented as identical90.2%86.3%Vals AIAs of 10/13/2026

LiveCodeBenchMedium · higher is betterTest setup not documented as identical87.2%86.9%Vals AIAs of 09/01/2026

MMLU ProChemistry · higher is betterTest setup not documented as identical91.8%89.8%Vals AIAs of 09/01/2026

SWE-bench Verified1-4 hours · higher is betterTest setup not documented as identical69%33.3%Vals AIAs of 09/01/2026

Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identical43.1%12.3%Vals AIAs of 10/26/2026

Terminal-Bench 2.1Medium · higher is betterTest setup not documented as identical67.3%70.9%Vals AIAs of 10/01/2026

EMBLBO · higher is betterTest setup not documented as identical53.7%45%Vals AIAs of 10/20/2026

Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identical60.3%47.3%Vals AIAs of 10/20/2026

Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identical86.8%75.8%Vals AIAs of 10/26/2026

LegalBenchRhetoric Tasks · higher is betterTest setup not documented as identical81.4%77.8%Vals AIAs of 10/13/2026

MMLU ProComputer Science · higher is betterTest setup not documented as identical88.3%86.6%Vals AIAs of 09/01/2026

SWE-bench Verified15 min - 1 hour · higher is betterTest setup not documented as identical85.8%70.5%Vals AIAs of 09/01/2026

Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identical58.6%30.1%Vals AIAs of 10/26/2026

EMBM&A · higher is betterTest setup not documented as identical64.8%60.4%Vals AIAs of 10/20/2026

Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identical70.9%45%Vals AIAs of 10/20/2026

Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identical25.9%11.1%Vals AIAs of 10/26/2026

Compare another matchup

First modelSecond model

More matchups

Compare Qwen 3.8 27B and MiMo-V2.5 with other leading models.

View the complete LLM comparison

Qwen 3.8 27Bvs.MiMo-V2.5

Qwen 3.8 27B

MiMo-V2.5

Where is the difference?

See for yourself: same task, one attempt

SVG short test

Qwen 3.8 27B

MiMo-V2.5

Pelican on a bicycle

All data side by side

Shared benchmarks

Compare another matchup

Related LLM comparisons