LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Mistral Medium 3.5 vs MiMo-V2.5

Updated October 21, 2026. 75 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Mistral Medium 3.5 Replace MiMo-V2.5
Mistral Medium 3.5Mistral AI
Coding
9.2
Overall
14.2
Output $/M
$7.50
9
MiMo-V2.5Xiaomi
Coding
34.0
Overall
21.8
Output $/M
$0.238
65
vs boards won of 75 shared, 1 tied

Decision reading

Pick MiMo-V2.5 for coding: it scores 34.0 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5.

Pick Mistral Medium 3.5 when what matters is ALE-Bench or τ²-Bench Telecom, where it leads.

Model AMistral Medium 3.5Mistral AI9.2/1001 independent benchmark$6.02 per solved taskModel BMiMo-V2.5Xiaomi34.0/1001 independent benchmark$0.01 per solved task
Shared results
75
Mistral Medium 3.5 only
5
MiMo-V2.5 only
5
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
Mistral Medium 3.5 9.2 from 1 benchmark, MiMo-V2.5 34.0 from 1 benchmark.
Widest category
Web design, 18.8 points apart on average over 8 shared benchmarks.
Widest single gap
GPQA Diamond: Mistral Medium 3.5 34.9% against MiMo-V2.5 81.6%, 46.7 points apart on a 0 to 100 scale.
Output price
Mistral Medium 3.5 $7.50 against MiMo-V2.5 $0.238 per million output tokens, 31.5x apart.
Context window
Mistral Medium 3.5 takes 262K 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
CategoryMistral Medium 3.5BarsMiMo-V2.5Ties
Coding112
Intelligence01
Agentic work141 tie
Reasoning08
Math03
Knowledge27
Web design08
General522
All shared boards9651 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index112
Coding benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
LMArena WebDev12641438MiMo-V2.5
AA Coding Index46.956.8MiMo-V2.5
LiveCodeBench (Vals AI)Not measured81.5%Only MiMo-V2.5 measured
SWE-bench Verified (Vals AI)66.4%71.0%MiMo-V2.5
Vibe Code Bench (Vals AI)2.9%42.2%MiMo-V2.5
Code migration (Vals AI)5.1%14.2%MiMo-V2.5
Terminal-Bench 2.1 (Vals AI)39.0%60.7%MiMo-V2.5
SciCode40.2%43.9%MiMo-V2.5
Terminal-Bench Hard (Artificial Analysis run)33.3%41.7%MiMo-V2.5
ALE-Bench764.0514.0Mistral Medium 3.5
LMArena Text: coding14601469MiMo-V2.5
LMArena Text: software and IT14581463MiMo-V2.5
LMArena WebDev: React12541425MiMo-V2.5
LMArena WebDev: HTML13081429MiMo-V2.5
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
AA Intelligence Index14.221.8MiMo-V2.5
Epoch Capabilities Index141.4Not measuredOnly Mistral Medium 3.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
Agentic work benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
AA Agentic Index7.015.8MiMo-V2.5
Finance Agent (Vals AI)32.1%36.7%MiMo-V2.5
Tax Agent Bench (Vals AI)4.5%7.8%MiMo-V2.5
Legal Research Bench (Vals AI)9.1%9.1%Tie
Excel Modeling Benchmark (Vals AI)11.2%55.1%MiMo-V2.5
τ²-Bench Telecom94.2%90.6%Mistral Medium 3.5
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
GPQA Diamond34.9%81.6%MiMo-V2.5
MMMU Pro (Vals AI)Not measured80.0%Only MiMo-V2.5 measured
GPQA Diamond (Artificial Analysis run)74.8%84.9%MiMo-V2.5
Humanity's Last Exam (Artificial Analysis run)13.8%27.2%MiMo-V2.5
LMArena Text: hard prompts14361450MiMo-V2.5
LMArena Text: expert14321459MiMo-V2.5
LMArena Text: hard prompts in English14451461MiMo-V2.5
LMArena Vision: diagrams12541269MiMo-V2.5
LMArena Vision: homework12301262MiMo-V2.5
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
ProofBench9.0%16.0%MiMo-V2.5
LMArena Text: math14311436MiMo-V2.5
LMArena Text: mathematical work14401451MiMo-V2.5
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index27
Knowledge benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
MMLU Pro75.3%82.9%MiMo-V2.5
LegalBench (Vals AI)Not measured78.9%Only MiMo-V2.5 measured
CaseLaw (Vals AI)44.2%Not measuredOnly Mistral Medium 3.5 measured
CorpFin (Vals AI)58.8%59.9%MiMo-V2.5
TaxEval (Vals AI)68.0%71.8%MiMo-V2.5
MortgageTax (Vals AI)28.9%59.3%MiMo-V2.5
MedCode (Vals AI)33.8%31.9%Mistral Medium 3.5
LMArena Text: science14281440MiMo-V2.5
LMArena Text: medicine and healthcare14091432MiMo-V2.5
LMArena Text: legal and government14371425Mistral Medium 3.5
LMArena Text: business and finance14261432MiMo-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 index08
Web design benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
Design Arena: websites11421266MiMo-V2.5
Design Arena: UI components10791257MiMo-V2.5
Design Arena: game dev10791249MiMo-V2.5
Design Arena: data viz11201249MiMo-V2.5
Design Arena: 3D10611216MiMo-V2.5
Design Arena: all code categories11221260MiMo-V2.5
Design Arena: SVG9491178MiMo-V2.5
Design Arena: ASCII art10621141MiMo-V2.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index522
General benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-V2.5Leader
SAGE (Vals AI)37.6%43.3%MiMo-V2.5
MedScribe (Vals AI)67.7%72.2%MiMo-V2.5
Vals Multimodal Index34.8%52.8%MiMo-V2.5
IFBench68.8%67.1%Mistral Medium 3.5
Long context reasoning (AA-LCR)69.3%73.0%MiMo-V2.5
DTBench75.5%Not measuredOnly Mistral Medium 3.5 measured
LMCA26.1%Not measuredOnly Mistral Medium 3.5 measured
Surface Evolver Bench26.9%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text14211428MiMo-V2.5
LMArena Text: instruction following14151435MiMo-V2.5
LMArena Text: creative writing13741393MiMo-V2.5
LMArena Vision12221247MiMo-V2.5
LMArena Text: English14331447MiMo-V2.5
LMArena Text: non-English14041405MiMo-V2.5
LMArena Text: Chinese14441469MiMo-V2.5
LMArena Text: German14531421Mistral Medium 3.5
LMArena Text: JapaneseNot measured1306Only MiMo-V2.5 measured
LMArena Text: Korean13841361Mistral Medium 3.5
LMArena Text: French14481448Mistral Medium 3.5
LMArena Text: Spanish14111414MiMo-V2.5
LMArena Text: Russian13951396MiMo-V2.5
LMArena Text: Polish14301413Mistral Medium 3.5
LMArena Text: multi-turn14231445MiMo-V2.5
LMArena Text: longer queries14151445MiMo-V2.5
LMArena Text: writing and language13841409MiMo-V2.5
LMArena Text: entertainment and media13821399MiMo-V2.5
LMArena Vision: English12401259MiMo-V2.5
LMArena Vision: Chinese12441326MiMo-V2.5
LMArena Vision: reading text12331256MiMo-V2.5
LMArena Vision: humor12161226MiMo-V2.5
LMArena Vision: recognizing thingsNot measured1189Only MiMo-V2.5 measured
LMArena Vision: creative writing11981230MiMo-V2.5
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mistral Medium 3.5 and MiMo-V2.5
BenchmarkMistral Medium 3.5MiMo-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

Mistral Medium 3.5$0.0053Fits in one request
MiMo-V2.5$0.0002Fits in one request

MiMo-V2.5 costs less

Repository review

50K input + 3K output tokens

Mistral Medium 3.5$0.098Fits in one request
MiMo-V2.5$0.0067Fits in one request

MiMo-V2.5 costs less

Agent loop

200K input + 10K output tokens

Mistral Medium 3.5$0.375Fits 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 Mistral Medium 3.5 and MiMo-V2.5
SpecificationMistral Medium 3.5Xiaomi MiMo-V2.5
MakerMistral AIXiaomi
WeightsNo public weights listedOpen weights
ReleasedApril 30, 2026April 22, 2026
Context window262K1.05M
Input $/Mtok$1.50$0.119
Output $/Mtok$7.50$0.238
Coding index9.234.0
Independent measurements behind it11
Cost per solved task$6.02$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Medium 3.5 better than MiMo-V2.5 for coding?

Pick MiMo-V2.5 for coding: it scores 34.0 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5. Pick Mistral Medium 3.5 when what matters is ALE-Bench or τ²-Bench Telecom, where it leads.

Which is cheaper, Mistral Medium 3.5 or MiMo-V2.5?

Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens; MiMo-V2.5 costs $0.119 and $0.238. Per solved SWE-bench Verified task, Mistral Medium 3.5 costs $6.02 and MiMo-V2.5 $0.01.

Which has the bigger context window, Mistral Medium 3.5 or MiMo-V2.5?

MiMo-V2.5, with 1.05M tokens against 262K.

How many benchmarks is the Mistral Medium 3.5 vs MiMo-V2.5 comparison based on?

75 benchmarks have a result for both models as of October 21, 2026. Mistral Medium 3.5'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