Enter opens the highlighted result. Esc closes.

GPT-5.6 Luna vs MiMo-V2.5

GPT-5.6 Luna leads MiMo-V2.5 on coding, 58.0 to 50.0 on the Vibe Coding Index, and MiMo-V2.5 costs 3.6x less per output token ($0.336 vs $1.20 per million). Updated October 22, 2026; 75 benchmarks have a result for both.

Replace GPT-5.6 Luna Replace MiMo-V2.5
GPT-5.6 LunaOpenAI
Coding
58.0
Overall
61.6
Output $/M
$1.20
59
MiMo-V2.5Xiaomi
Coding
50.0
Overall
50.7
Output $/M
$0.336
16
vs boards won of 75 shared

GPT-5.6 Luna or MiMo-V2.5: which to pick

Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 50.0 for MiMo-V2.5.

Pick MiMo-V2.5 for output tokens 3.6x cheaper ($0.336 vs $1.20 per million) and a lower cost per solved task ($0.01 against $0.04).

Model AGPT-5.6 LunaOpenAI58.0/1006 independent benchmarks$0.04 per solved taskModel BMiMo-V2.5Xiaomi50.0/1003 independent benchmarks$0.01 per solved task
Shared results
75
GPT-5.6 Luna only
44
MiMo-V2.5 only
5
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
GPT-5.6 Luna 58.0 from 6 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
Widest category
Agentic work, 20.2 points apart on average over 5 shared benchmarks.
Widest single gap
ProofBench: GPT-5.6 Luna 60.0% against MiMo-V2.5 16.0%, 44.0 points apart on a 0 to 100 scale.
Output price
GPT-5.6 Luna $1.20 against MiMo-V2.5 $0.336 per million output tokens, 3.6x apart.
Context window
Both take 1.05M tokens.

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
CategoryGPT-5.6 LunaBarsMiMo-V2.5Ties
Coding111
Intelligence10
Agentic work50
Reasoning81
Math30
Knowledge82
Web design26
General216
All shared boards5916
CodingLike-for-likeSix of these boards feed the Vibe Coding Index111
Coding benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
LiveBench coding73.6%Not measuredOnly GPT-5.6 Luna measured
LMArena WebDev15181438GPT-5.6 Luna
AA Coding Index71.456.8GPT-5.6 Luna
LiveCodeBench (Vals AI)Not measured81.5%Only MiMo-V2.5 measured
SWE-bench Verified (Vals AI)93.0%71.0%GPT-5.6 Luna
Terminal-Bench 4 (Vals AI)11.6%Not measuredOnly GPT-5.6 Luna measured
Vibe Code Bench (Vals AI)77.1%42.2%GPT-5.6 Luna
Code migration (Vals AI)44.5%14.2%GPT-5.6 Luna
ProgramBench (Vals AI)0.0%Not measuredOnly GPT-5.6 Luna measured
IOI (Vals AI)61.8%Not measuredOnly GPT-5.6 Luna measured
Terminal-Bench 2.1 (Vals AI)79.0%60.7%GPT-5.6 Luna
Vibe Code Bench 1-100 (Vals AI)22.6%Not measuredOnly GPT-5.6 Luna measured
SkillsBench (Vals AI)60.5%Not measuredOnly GPT-5.6 Luna measured
CyberBench (Vals AI)73.6%Not measuredOnly GPT-5.6 Luna measured
SciCode53.6%43.9%GPT-5.6 Luna
Terminal-Bench Hard (Artificial Analysis run)Not measured41.7%Only MiMo-V2.5 measured
FrontierCode39.8%Not measuredOnly GPT-5.6 Luna measured
WeirdML60.9%Not measuredOnly GPT-5.6 Luna measured
ALE-Bench1667.4514.0GPT-5.6 Luna
LMArena Text: coding14661469MiMo-V2.5
LMArena Text: software and IT14631463GPT-5.6 Luna
LMArena WebDev: React15081425GPT-5.6 Luna
LMArena WebDev: HTML15201429GPT-5.6 Luna
LMArena WebDev: from an image1517Not measuredOnly GPT-5.6 Luna measured
SciCode6.2%Not measuredOnly GPT-5.6 Luna measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
AA Intelligence Index37.321.8GPT-5.6 Luna
Epoch Capabilities Index156.5Not measuredOnly GPT-5.6 Luna measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
AA Agentic Index42.115.8GPT-5.6 Luna
LiveBench research51.0%Not measuredOnly GPT-5.6 Luna measured
LiveBench browser68.0%Not measuredOnly GPT-5.6 Luna measured
LiveBench long agentic30.4%Not measuredOnly GPT-5.6 Luna measured
SREBench (Vals AI)1.5%Not measuredOnly GPT-5.6 Luna measured
Finance Agent (Vals AI)55.0%36.7%GPT-5.6 Luna
Tax Agent Bench (Vals AI)24.8%7.8%GPT-5.6 Luna
Legal Research Bench (Vals AI)36.5%9.1%GPT-5.6 Luna
Excel Modeling Benchmark (Vals AI)67.1%55.1%GPT-5.6 Luna
BioMysteryBench (Vals AI)61.5%Not measuredOnly GPT-5.6 Luna measured
Terminal-Bench-Science (Vals AI)0.0%Not measuredOnly GPT-5.6 Luna measured
Vals Science Index25.3%Not measuredOnly GPT-5.6 Luna measured
τ²-Bench TelecomNot measured90.6%Only MiMo-V2.5 measured
APEX-Agents43.0%Not measuredOnly GPT-5.6 Luna measured
BALROG45.6%Not measuredOnly GPT-5.6 Luna measured
Vending-Bench 2$4,095Not measuredOnly GPT-5.6 Luna measured
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index81
Reasoning benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
GPQA Diamond91.7%81.6%GPT-5.6 Luna
LiveBench reasoning85.6%Not measuredOnly GPT-5.6 Luna measured
MysteryMechanism (Vals AI)14.4%Not measuredOnly GPT-5.6 Luna measured
MMMU Pro (Vals AI)85.0%80.0%GPT-5.6 Luna
GPQA Diamond (Artificial Analysis run)91.1%84.9%GPT-5.6 Luna
Humanity's Last Exam (Artificial Analysis run)39.5%27.2%GPT-5.6 Luna
GPQA Diamond (Epoch AI run)91.6%Not measuredOnly GPT-5.6 Luna measured
ARC-AGI88.0%Not measuredOnly GPT-5.6 Luna measured
ARC-AGI-259.5%Not measuredOnly GPT-5.6 Luna measured
SimpleBench46.8%Not measuredOnly GPT-5.6 Luna measured
Chess puzzles43.0%Not measuredOnly GPT-5.6 Luna measured
Mystery game puzzles21.0%Not measuredOnly GPT-5.6 Luna measured
LMArena Text: hard prompts14511450GPT-5.6 Luna
LMArena Text: expert14781459GPT-5.6 Luna
LMArena Text: hard prompts in English14601461MiMo-V2.5
LMArena Vision: diagrams12731269GPT-5.6 Luna
LMArena Vision: homework12821262GPT-5.6 Luna
Kagi LLM Benchmark49.1%Not measuredOnly GPT-5.6 Luna measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
OTIS Mock AIME98.3%Not measuredOnly GPT-5.6 Luna measured
FrontierMath, tiers 1 to 382.1%Not measuredOnly GPT-5.6 Luna measured
FrontierMath, tier 461.0%Not measuredOnly GPT-5.6 Luna measured
ProofBench60.0%16.0%GPT-5.6 Luna
LMArena Text: math14591436GPT-5.6 Luna
LMArena Text: mathematical work14701451GPT-5.6 Luna
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
Knowledge benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
MMLU Pro86.0%82.9%GPT-5.6 Luna
LegalBench (Vals AI)84.0%78.9%GPT-5.6 Luna
CorpFin (Vals AI)64.2%59.9%GPT-5.6 Luna
TaxEval (Vals AI)76.2%71.8%GPT-5.6 Luna
MortgageTax (Vals AI)67.3%59.3%GPT-5.6 Luna
MedCode (Vals AI)42.4%31.9%GPT-5.6 Luna
SimpleQA Verified41.0%Not measuredOnly GPT-5.6 Luna measured
LMArena Text: science14331440MiMo-V2.5
LMArena Text: medicine and healthcare13991432MiMo-V2.5
LMArena Text: legal and government14461425GPT-5.6 Luna
LMArena Text: business and finance14391432GPT-5.6 Luna
FACTS Benchmark Suite35.0%Not measuredOnly GPT-5.6 Luna measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index26
Web design benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
Design Arena: websites12551265MiMo-V2.5
Design Arena: UI components12481255MiMo-V2.5
Design Arena: game dev11941249MiMo-V2.5
Design Arena: data viz12111250MiMo-V2.5
Design Arena: 3D11211215MiMo-V2.5
Design Arena: all code categories12311260MiMo-V2.5
Design Arena: SVG11941179GPT-5.6 Luna
Design Arena: ASCII art11421140GPT-5.6 Luna
LiveBench design76.0%Not measuredOnly GPT-5.6 Luna measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index216
General benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-V2.5Leader
LiveBench data analysis78.0%Not measuredOnly GPT-5.6 Luna measured
Public Benefits Bench (Vals AI)61.2%Not measuredOnly GPT-5.6 Luna measured
SAGE (Vals AI)44.2%43.3%GPT-5.6 Luna
MedScribe (Vals AI)84.4%72.2%GPT-5.6 Luna
Vals Multimodal Index69.1%52.8%GPT-5.6 Luna
IFBenchNot measured67.1%Only MiMo-V2.5 measured
Long context reasoning (AA-LCR)83.7%73.0%GPT-5.6 Luna
DTBench89.1%Not measuredOnly GPT-5.6 Luna measured
LMCA48.5%Not measuredOnly GPT-5.6 Luna measured
Surface Evolver Bench61.9%Not measuredOnly GPT-5.6 Luna measured
Furniture assembly42.5%Not measuredOnly GPT-5.6 Luna measured
LMArena Text14311428GPT-5.6 Luna
LMArena Text: instruction following14371435GPT-5.6 Luna
LMArena Text: creative writing13961393GPT-5.6 Luna
LMArena Vision12571247GPT-5.6 Luna
LMArena Text: English14411447MiMo-V2.5
LMArena Text: non-English14171405GPT-5.6 Luna
LMArena Text: Chinese14701469GPT-5.6 Luna
LMArena Text: German14551421GPT-5.6 Luna
LMArena Text: Japanese14151306GPT-5.6 Luna
LMArena Text: Korean14151361GPT-5.6 Luna
LMArena Text: French14581448GPT-5.6 Luna
LMArena Text: Spanish14461414GPT-5.6 Luna
LMArena Text: Russian14271396GPT-5.6 Luna
LMArena Text: Polish14051413MiMo-V2.5
LMArena Text: multi-turn14341445MiMo-V2.5
LMArena Text: longer queries14361445MiMo-V2.5
LMArena Text: writing and language14191409GPT-5.6 Luna
LMArena Text: entertainment and media14021399GPT-5.6 Luna
LMArena Vision: English12631259GPT-5.6 Luna
LMArena Vision: Chinese12941326MiMo-V2.5
LMArena Vision: reading text12641256GPT-5.6 Luna
LMArena Vision: humor11901226MiMo-V2.5
LMArena Vision: recognizing thingsNot measured1189Only MiMo-V2.5 measured
LMArena Vision: creative writing12571230GPT-5.6 Luna
LMArena Document1457Not measuredOnly GPT-5.6 Luna measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.6 Luna and MiMo-V2.5
BenchmarkGPT-5.6 LunaMiMo-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

GPT-5.6 Luna$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

GPT-5.6 Luna$0.014Fits in one request
MiMo-V2.5$0.0094Fits in one request

MiMo-V2.5 costs less

Agent loop

200K input + 10K output tokens

GPT-5.6 Luna$0.052Fits 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 GPT-5.6 Luna and MiMo-V2.5
SpecificationOpenAI GPT-5.6 LunaXiaomi MiMo-V2.5
MakerOpenAIXiaomi
WeightsNo public weights listedOpen weights
ReleasedJuly 9, 2026April 22, 2026
Context window1.05M1.05M
Input $/Mtok$0.20$0.168
Output $/Mtok$1.20$0.336
Coding index58.050.0
Independent measurements behind it63
Cost per solved task$0.04$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.6 Luna better than MiMo-V2.5 for coding?

Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 50.0 for MiMo-V2.5. Pick MiMo-V2.5 for output tokens 3.6x cheaper ($0.336 vs $1.20 per million) and a lower cost per solved task ($0.01 against $0.04).

Which is cheaper, GPT-5.6 Luna or MiMo-V2.5?

GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Per solved SWE-bench Verified task, GPT-5.6 Luna costs $0.04 and MiMo-V2.5 $0.01.

Which has the bigger context window, GPT-5.6 Luna or MiMo-V2.5?

Neither: both take 1.05M tokens.

How many benchmarks is the GPT-5.6 Luna vs MiMo-V2.5 comparison based on?

75 benchmarks have a result for both models as of October 22, 2026. GPT-5.6 Luna's coding index rests on 6 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

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gpt-5-6-luna-vs-xiaomi-mimo-v2-5" title="GPT-5.6 Luna vs MiMo-V2.5, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gpt-5-6-luna-vs-xiaomi-mimo-v2-5">LLMBenchmark.ai, GPT-5.6 Luna vs MiMo-V2.5</a></p>