LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.1 Flash Lite Preview vs MiMo-V2.5

Updated October 21, 2026. 72 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.1 Flash Lite Preview Replace MiMo-V2.5
Gemini 3.1 Flash Lite PreviewGoogle
Coding
8.1
Overall
15.6
Output $/M
$1.50
20
MiMo-V2.5Xiaomi
Coding
34.0
Overall
21.8
Output $/M
$0.238
52
vs boards won of 72 shared

Decision reading

Pick MiMo-V2.5 for coding: it scores 34.0 on the Vibe Coding Index against 8.1 for Gemini 3.1 Flash Lite Preview.

Pick Gemini 3.1 Flash Lite Preview when what matters is ALE-Bench or MMMU Pro (Vals AI), where it leads.

Model AGemini 3.1 Flash Lite PreviewGoogle8.1/1001 independent benchmark$0.18 per solved taskModel BMiMo-V2.5Xiaomi34.0/1001 independent benchmark$0.01 per solved task
Shared results
72
Gemini 3.1 Flash Lite Preview only
5
MiMo-V2.5 only
8
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
Gemini 3.1 Flash Lite Preview 8.1 from 1 benchmark, MiMo-V2.5 34.0 from 1 benchmark.
Widest category
Web design, 20.3 points apart on average over 8 shared benchmarks.
Widest single gap
Excel Modeling Benchmark (Vals AI): Gemini 3.1 Flash Lite Preview 8.6% against MiMo-V2.5 55.1%, 46.5 points apart on a 0 to 100 scale.
Output price
Gemini 3.1 Flash Lite Preview $1.50 against MiMo-V2.5 $0.238 per million output tokens, 6.3x apart.
Context window
Gemini 3.1 Flash Lite Preview takes 1.05M 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
CategoryGemini 3.1 Flash Lite PreviewBarsMiMo-V2.5Ties
Coding111
Intelligence01
Agentic work05
Reasoning25
Math02
Knowledge46
Web design17
General1215
All shared boards2052
CodingLike-for-likeFour of these boards feed the Vibe Coding Index111
Coding benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
LMArena WebDev12571438MiMo-V2.5
AA Coding Index34.756.8MiMo-V2.5
LiveCodeBench (Vals AI)80.1%81.5%MiMo-V2.5
SWE-bench Verified (Vals AI)62.8%71.0%MiMo-V2.5
Vibe Code Bench (Vals AI)0.0%42.2%MiMo-V2.5
Code migration (Vals AI)4.6%14.2%MiMo-V2.5
ProgramBench (Vals AI)0.0%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
Terminal-Bench 2.1 (Vals AI)34.1%60.7%MiMo-V2.5
SciCodeNot measured43.9%Only MiMo-V2.5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured41.7%Only MiMo-V2.5 measured
ALE-Bench797.7514.0Gemini 3.1 Flash Lite Preview
LMArena Text: coding14001469MiMo-V2.5
LMArena Text: software and IT14131463MiMo-V2.5
LMArena WebDev: React12451425MiMo-V2.5
LMArena WebDev: HTML12761429MiMo-V2.5
LMArena WebDev: from an image1336Not measuredOnly Gemini 3.1 Flash Lite Preview measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
AA Intelligence Index15.621.8MiMo-V2.5
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
AA Agentic Index1.615.8MiMo-V2.5
Finance Agent (Vals AI)30.0%36.7%MiMo-V2.5
Tax Agent Bench (Vals AI)3.1%7.8%MiMo-V2.5
Legal Research Bench (Vals AI)3.4%9.1%MiMo-V2.5
Excel Modeling Benchmark (Vals AI)8.6%55.1%MiMo-V2.5
τ²-Bench TelecomNot measured90.6%Only MiMo-V2.5 measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index25
Reasoning benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
GPQA Diamond81.1%81.6%MiMo-V2.5
MMMU Pro (Vals AI)82.5%80.0%Gemini 3.1 Flash Lite Preview
GPQA Diamond (Artificial Analysis run)Not measured84.9%Only MiMo-V2.5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured27.2%Only MiMo-V2.5 measured
LMArena Text: hard prompts14071450MiMo-V2.5
LMArena Text: expert13981459MiMo-V2.5
LMArena Text: hard prompts in English14031461MiMo-V2.5
LMArena Vision: diagrams12421269MiMo-V2.5
LMArena Vision: homework12711262Gemini 3.1 Flash Lite Preview
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
AIME83.3%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
ProofBenchNot measured16.0%Only MiMo-V2.5 measured
LMArena Text: math14281436MiMo-V2.5
LMArena Text: mathematical work14171451MiMo-V2.5
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index46
Knowledge benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
MMLU Pro86.2%82.9%Gemini 3.1 Flash Lite Preview
LegalBench (Vals AI)83.8%78.9%Gemini 3.1 Flash Lite Preview
CaseLaw (Vals AI)55.0%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
CorpFin (Vals AI)59.4%59.9%MiMo-V2.5
TaxEval (Vals AI)71.8%71.8%MiMo-V2.5
MortgageTax (Vals AI)68.0%59.3%Gemini 3.1 Flash Lite Preview
MedCode (Vals AI)47.6%31.9%Gemini 3.1 Flash Lite Preview
LMArena Text: science14251440MiMo-V2.5
LMArena Text: medicine and healthcare14281432MiMo-V2.5
LMArena Text: legal and government14181425MiMo-V2.5
LMArena Text: business and finance13891432MiMo-V2.5
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
Design Arena: websites10831266MiMo-V2.5
Design Arena: UI components10711257MiMo-V2.5
Design Arena: game dev10291249MiMo-V2.5
Design Arena: data viz10451249MiMo-V2.5
Design Arena: 3D10481216MiMo-V2.5
Design Arena: all code categories10721260MiMo-V2.5
Design Arena: SVG10521178MiMo-V2.5
Design Arena: ASCII art11661141Gemini 3.1 Flash Lite Preview
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1215
General benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-V2.5Leader
SAGE (Vals AI)49.5%43.3%Gemini 3.1 Flash Lite Preview
MedScribe (Vals AI)63.9%72.2%MiMo-V2.5
Vals Multimodal Index41.4%52.8%MiMo-V2.5
IFBenchNot measured67.1%Only MiMo-V2.5 measured
Long context reasoning (AA-LCR)Not measured73.0%Only MiMo-V2.5 measured
LMArena Text14161428MiMo-V2.5
LMArena Text: instruction following13771435MiMo-V2.5
LMArena Text: creative writing14011393Gemini 3.1 Flash Lite Preview
LMArena Vision12401247MiMo-V2.5
LMArena Text: English14141447MiMo-V2.5
LMArena Text: non-English14101405Gemini 3.1 Flash Lite Preview
LMArena Text: Chinese14601469MiMo-V2.5
LMArena Text: German14301421Gemini 3.1 Flash Lite Preview
LMArena Text: Japanese14131306Gemini 3.1 Flash Lite Preview
LMArena Text: Korean13921361Gemini 3.1 Flash Lite Preview
LMArena Text: French14241448MiMo-V2.5
LMArena Text: Spanish14211414Gemini 3.1 Flash Lite Preview
LMArena Text: Russian14201396Gemini 3.1 Flash Lite Preview
LMArena Text: Polish14431413Gemini 3.1 Flash Lite Preview
LMArena Text: multi-turn14171445MiMo-V2.5
LMArena Text: longer queries13941445MiMo-V2.5
LMArena Text: writing and language14081409MiMo-V2.5
LMArena Text: entertainment and media13861399MiMo-V2.5
LMArena Vision: English12321259MiMo-V2.5
LMArena Vision: Chinese12781326MiMo-V2.5
LMArena Vision: reading text12461256MiMo-V2.5
LMArena Vision: humor12661226Gemini 3.1 Flash Lite Preview
LMArena Vision: captioning1259Not measuredOnly Gemini 3.1 Flash Lite Preview measured
LMArena Vision: recognizing things13081189Gemini 3.1 Flash Lite Preview
LMArena Vision: creative writing12481230Gemini 3.1 Flash Lite Preview
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.1 Flash Lite Preview and MiMo-V2.5
BenchmarkGemini 3.1 Flash Lite PreviewMiMo-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

Gemini 3.1 Flash Lite Preview$0.0010Fits in one request
MiMo-V2.5$0.0002Fits in one request

MiMo-V2.5 costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Flash Lite Preview$0.017Fits in one request
MiMo-V2.5$0.0067Fits in one request

MiMo-V2.5 costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Flash Lite Preview$0.065Fits in one request
MiMo-V2.5$0.026Fits 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 Gemini 3.1 Flash Lite Preview and MiMo-V2.5
SpecificationGoogle Gemini 3.1 Flash Lite PreviewXiaomi MiMo-V2.5
MakerGoogleXiaomi
WeightsNo public weights listedOpen weights
ReleasedMarch 3, 2026April 22, 2026
Context window1.05M1.05M
Input $/Mtok$0.25$0.119
Output $/Mtok$1.50$0.238
Coding index8.134.0
Independent measurements behind it11
Cost per solved task$0.18$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.1 Flash Lite Preview better than MiMo-V2.5 for coding?

Pick MiMo-V2.5 for coding: it scores 34.0 on the Vibe Coding Index against 8.1 for Gemini 3.1 Flash Lite Preview. Pick Gemini 3.1 Flash Lite Preview when what matters is ALE-Bench or MMMU Pro (Vals AI), where it leads.

Which is cheaper, Gemini 3.1 Flash Lite Preview or MiMo-V2.5?

Gemini 3.1 Flash Lite Preview costs $0.25 per million input tokens and $1.50 per million output tokens; MiMo-V2.5 costs $0.119 and $0.238. Per solved SWE-bench Verified task, Gemini 3.1 Flash Lite Preview costs $0.18 and MiMo-V2.5 $0.01.

Which has the bigger context window, Gemini 3.1 Flash Lite Preview or MiMo-V2.5?

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

How many benchmarks is the Gemini 3.1 Flash Lite Preview vs MiMo-V2.5 comparison based on?

72 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Flash Lite Preview's coding index rests on 1 independent benchmark and MiMo-V2.5's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next