Enter opens the highlighted result. Esc closes.

Llama 4 Maverick vs MiMo-V2.5

MiMo-V2.5 leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 21.8 to 9.3, and MiMo-V2.5 costs 3.0x less per output token ($0.336 vs $1.00 per million). Updated October 22, 2026; 64 benchmarks have a result for both.

Replace Llama 4 Maverick Replace MiMo-V2.5
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
1
MiMo-V2.5Xiaomi
Coding
50.0
Overall
50.7
Output $/M
$0.336
63
vs boards won of 64 shared

Llama 4 Maverick or MiMo-V2.5: which to pick

Only MiMo-V2.5 has a coding score, 50.0 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding.

Pick Llama 4 Maverick for work measured by MedCode (Vals AI), where it leads.

Model ALlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved taskModel BMiMo-V2.5Xiaomi50.0/1003 independent benchmarks$0.01 per solved task
Shared results
64
Llama 4 Maverick only
21
MiMo-V2.5 only
16
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Llama 4 Maverick not benchmarked, MiMo-V2.5 50.0 from 3 benchmarks.
Widest category
Web design, 46.4 points apart on average over 6 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Llama 4 Maverick 17.8% against MiMo-V2.5 90.6%, 72.8 points apart on a 0 to 100 scale.
Output price
Llama 4 Maverick $1.00 against MiMo-V2.5 $0.336 per million output tokens, 3.0x apart.
Context window
Llama 4 Maverick takes 524K tokens, MiMo-V2.5 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryLlama 4 MaverickBarsMiMo-V2.5Ties
Coding07
Intelligence01
Agentic work02
Reasoning09
Math02
Knowledge19
Web design06
General027
All shared boards163
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
Coding benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
Aider polyglot15.6%Not measuredOnly Llama 4 Maverick measured
SWE-bench Verified21.0%Not measuredOnly Llama 4 Maverick measured
LMArena WebDevNot measured1438Only MiMo-V2.5 measured
AA Coding Index16.356.8MiMo-V2.5
LiveCodeBench (Vals AI)47.3%81.5%MiMo-V2.5
SWE-bench Verified (Vals AI)Not measured71.0%Only MiMo-V2.5 measured
Vibe Code Bench (Vals AI)Not measured42.2%Only MiMo-V2.5 measured
Code migration (Vals AI)Not measured14.2%Only MiMo-V2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured60.7%Only MiMo-V2.5 measured
LiveCodeBench (Artificial Analysis run)39.7%Not measuredOnly Llama 4 Maverick measured
SciCode31.7%43.9%MiMo-V2.5
Terminal-Bench Hard (Artificial Analysis run)6.8%41.7%MiMo-V2.5
WeirdML24.5%Not measuredOnly Llama 4 Maverick measured
ALE-Bench173.0514.0MiMo-V2.5
LMArena Text: coding13011469MiMo-V2.5
LMArena Text: software and IT12991463MiMo-V2.5
LMArena WebDev: ReactNot measured1425Only MiMo-V2.5 measured
LMArena WebDev: HTMLNot measured1429Only MiMo-V2.5 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
AA Intelligence Index9.321.8MiMo-V2.5
Epoch Capabilities Index132.2Not measuredOnly Llama 4 Maverick measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
AA Agentic Index0.615.8MiMo-V2.5
Finance Agent (Vals AI)Not measured36.7%Only MiMo-V2.5 measured
Tax Agent Bench (Vals AI)Not measured7.8%Only MiMo-V2.5 measured
Legal Research Bench (Vals AI)Not measured9.1%Only MiMo-V2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured55.1%Only MiMo-V2.5 measured
τ²-Bench Telecom17.8%90.6%MiMo-V2.5
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
Reasoning benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
GPQA Diamond69.4%81.6%MiMo-V2.5
MMMU Pro (Vals AI)71.7%80.0%MiMo-V2.5
GPQA Diamond (Artificial Analysis run)67.1%84.9%MiMo-V2.5
Humanity's Last Exam (Artificial Analysis run)4.9%27.2%MiMo-V2.5
ARC-AGI4.4%Not measuredOnly Llama 4 Maverick measured
ARC-AGI-20.0%Not measuredOnly Llama 4 Maverick measured
SimpleBench27.7%Not measuredOnly Llama 4 Maverick measured
LMArena Text: hard prompts12811450MiMo-V2.5
LMArena Text: expert12591459MiMo-V2.5
LMArena Text: hard prompts in English12951461MiMo-V2.5
LMArena Vision: diagrams11341269MiMo-V2.5
LMArena Vision: homework11641262MiMo-V2.5
Kagi LLM Benchmark55.9%Not measuredOnly Llama 4 Maverick measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
AIME25.2%Not measuredOnly Llama 4 Maverick measured
MATH 500 (Vals AI)85.2%Not measuredOnly Llama 4 Maverick measured
MGSM (Vals AI)92.4%Not measuredOnly Llama 4 Maverick measured
AA Math Index19.3Not measuredOnly Llama 4 Maverick measured
AIME 2025 (Artificial Analysis run)19.3%Not measuredOnly Llama 4 Maverick measured
ProofBenchNot measured16.0%Only MiMo-V2.5 measured
LMArena Text: math12991436MiMo-V2.5
LMArena Text: mathematical work12951451MiMo-V2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
MMLU Pro79.4%82.9%MiMo-V2.5
LegalBench (Vals AI)77.8%78.9%MiMo-V2.5
CorpFin (Vals AI)49.7%59.9%MiMo-V2.5
TaxEval (Vals AI)66.6%71.8%MiMo-V2.5
MortgageTax (Vals AI)58.5%59.3%MiMo-V2.5
MedQA (Vals AI)43.3%Not measuredOnly Llama 4 Maverick measured
MedCode (Vals AI)36.5%31.9%Llama 4 Maverick
MMLU Pro (Artificial Analysis run)80.9%Not measuredOnly Llama 4 Maverick measured
GeoBench52.0%Not measuredOnly Llama 4 Maverick measured
LMArena Text: science12881440MiMo-V2.5
LMArena Text: medicine and healthcare12751432MiMo-V2.5
LMArena Text: legal and government12861425MiMo-V2.5
LMArena Text: business and finance12601432MiMo-V2.5
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
Design Arena: websites8711266MiMo-V2.5
Design Arena: UI components8971255MiMo-V2.5
Design Arena: game dev8371249MiMo-V2.5
Design Arena: data viz8821250MiMo-V2.5
Design Arena: 3D9001215MiMo-V2.5
Design Arena: all code categories8791260MiMo-V2.5
Design Arena: SVGNot measured1180Only MiMo-V2.5 measured
Design Arena: ASCII artNot measured1140Only MiMo-V2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index027
General benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
SAGE (Vals AI)35.7%43.3%MiMo-V2.5
MedScribe (Vals AI)54.2%72.2%MiMo-V2.5
Vals Multimodal IndexNot measured52.8%Only MiMo-V2.5 measured
IFBench43.0%67.1%MiMo-V2.5
Long context reasoning (AA-LCR)50.0%73.0%MiMo-V2.5
DTBench61.9%Not measuredOnly Llama 4 Maverick measured
LMCA15.9%Not measuredOnly Llama 4 Maverick measured
Fiction.LiveBench46.2%Not measuredOnly Llama 4 Maverick measured
Creative writing (Lech Mazur)62.0%Not measuredOnly Llama 4 Maverick measured
LMArena Text12871428MiMo-V2.5
LMArena Text: instruction following12671435MiMo-V2.5
LMArena Text: creative writing12661393MiMo-V2.5
LMArena Vision11421247MiMo-V2.5
LMArena Text: English13031447MiMo-V2.5
LMArena Text: non-English12691405MiMo-V2.5
LMArena Text: Chinese12771469MiMo-V2.5
LMArena Text: German12911421MiMo-V2.5
LMArena Text: Japanese12061306MiMo-V2.5
LMArena Text: Korean12031361MiMo-V2.5
LMArena Text: French12591448MiMo-V2.5
LMArena Text: Spanish12931414MiMo-V2.5
LMArena Text: Russian12861396MiMo-V2.5
LMArena Text: Polish12751413MiMo-V2.5
LMArena Text: multi-turn12891445MiMo-V2.5
LMArena Text: longer queries12801445MiMo-V2.5
LMArena Text: writing and language12771409MiMo-V2.5
LMArena Text: entertainment and media12501399MiMo-V2.5
LMArena Vision: English11501259MiMo-V2.5
LMArena Vision: Chinese11411326MiMo-V2.5
LMArena Vision: reading text11431256MiMo-V2.5
LMArena Vision: humor11001226MiMo-V2.5
LMArena Vision: recognizing thingsNot measured1189Only MiMo-V2.5 measured
LMArena Vision: creative writing10991230MiMo-V2.5
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Llama 4 Maverick and MiMo-V2.5
BenchmarkLlama 4 MaverickMiMo-V2.5Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Llama 4 Maverick$0.0008Fits in one request
MiMo-V2.5$0.0003Fits in one request

MiMo-V2.5 costs less

Repository review

50K input + 3K output tokens

Llama 4 Maverick$0.021Fits in one request
MiMo-V2.5$0.0094Fits in one request

MiMo-V2.5 costs less

Agent loop

200K input + 10K output tokens

Llama 4 Maverick$0.080Fits in one request
MiMo-V2.5$0.037Fits in one request

MiMo-V2.5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Llama 4 Maverick and MiMo-V2.5
SpecificationMeta Llama 4 MaverickXiaomi MiMo-V2.5
MakerMeta LlamaXiaomi
WeightsOpen weightsOpen weights
ReleasedApril 5, 2025April 22, 2026
Context window524K1.05M
Input $/Mtok$0.35$0.168
Output $/Mtok$1.00$0.336
Coding indexNot benchmarked50.0
Independent measurements behind it03
Cost per solved task$1.491$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 4 Maverick better than MiMo-V2.5 for coding?

Only MiMo-V2.5 has a coding score, 50.0 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding. Pick Llama 4 Maverick for work measured by MedCode (Vals AI), where it leads.

Which is cheaper, Llama 4 Maverick or MiMo-V2.5?

Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Per solved SWE-bench Verified task, Llama 4 Maverick costs $1.491 and MiMo-V2.5 $0.01.

Which has the bigger context window, Llama 4 Maverick or MiMo-V2.5?

MiMo-V2.5, with 1.05M tokens against 524K.

How many benchmarks is the Llama 4 Maverick vs MiMo-V2.5 comparison based on?

64 benchmarks have a result for both models as of October 22, 2026. Llama 4 Maverick's coding index rests on 0 independent benchmarks and MiMo-V2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next