LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs MiMo-V2.5

Updated October 21, 2026. 62 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Haiku 4.5 Replace MiMo-V2.5
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
8
MiMo-V2.5Xiaomi
Coding
34.0
Overall
21.8
Output $/M
$0.238
54
vs boards won of 62 shared

Decision reading

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 34.0 for MiMo-V2.5.

Pick MiMo-V2.5 when output tokens cost 21.0x less, or when a solved task costs $0.01 against $0.56.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BMiMo-V2.5Xiaomi34.0/1001 independent benchmark$0.01 per solved task
Shared results
62
Claude Haiku 4.5 only
32
MiMo-V2.5 only
18
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
Claude Haiku 4.5 49.8 from 3 benchmarks, MiMo-V2.5 34.0 from 1 benchmark.
Widest category
Web design, 16.0 points apart on average over 8 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against MiMo-V2.5 81.5%, 40.3 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against MiMo-V2.5 $0.238 per million output tokens, 21.0x apart.
Context window
Claude Haiku 4.5 takes 200K 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
CategoryClaude Haiku 4.5BarsMiMo-V2.5Ties
Coding011
Intelligence01
Agentic work14
Reasoning05
Math02
Knowledge46
Web design08
General317
All shared boards854
CodingLike-for-likeFour of these boards feed the Vibe Coding Index011
Coding benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
SWE-bench Verified66.6%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301438MiMo-V2.5
AA Coding Index43.956.8MiMo-V2.5
LiveCodeBench (Vals AI)41.2%81.5%MiMo-V2.5
SWE-bench Verified (Vals AI)66.6%71.0%MiMo-V2.5
Vibe Code Bench (Vals AI)11.4%42.2%MiMo-V2.5
Code migration (Vals AI)7.5%14.2%MiMo-V2.5
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 2.1 (Vals AI)43.8%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
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
WeirdML45.4%Not measuredOnly Claude Haiku 4.5 measured
ALE-BenchNot measured514.0Only MiMo-V2.5 measured
LMArena Text: coding14541469MiMo-V2.5
LMArena Text: software and IT14391463MiMo-V2.5
LMArena WebDev: React13261425MiMo-V2.5
LMArena WebDev: HTML13181429MiMo-V2.5
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
AA Intelligence Index16.921.8MiMo-V2.5
Epoch Capabilities Index142.2Not measuredOnly Claude Haiku 4.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
Agentic work benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
AA Agentic Index8.015.8MiMo-V2.5
LiveBench research42.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench browser40.0%Not measuredOnly Claude Haiku 4.5 measured
LiveBench long agentic11.1%Not measuredOnly Claude Haiku 4.5 measured
Finance Agent (Vals AI)31.0%36.7%MiMo-V2.5
Tax Agent Bench (Vals AI)5.9%7.8%MiMo-V2.5
Legal Research Bench (Vals AI)10.6%9.1%Claude Haiku 4.5
Excel Modeling Benchmark (Vals AI)22.7%55.1%MiMo-V2.5
τ²-Bench TelecomNot measured90.6%Only MiMo-V2.5 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
GPQA Diamond72.2%81.6%MiMo-V2.5
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%80.0%MiMo-V2.5
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
GPQA Diamond (Epoch AI run)71.2%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
Chess puzzles8.0%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: hard prompts14211450MiMo-V2.5
LMArena Text: expert14431459MiMo-V2.5
LMArena Text: hard prompts in English14351461MiMo-V2.5
LMArena Vision: diagramsNot measured1269Only MiMo-V2.5 measured
LMArena Vision: homeworkNot measured1262Only MiMo-V2.5 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
AIME82.7%Not measuredOnly Claude Haiku 4.5 measured
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%Not measuredOnly Claude Haiku 4.5 measured
ProofBenchNot measured16.0%Only MiMo-V2.5 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981436MiMo-V2.5
LMArena Text: mathematical work14301451MiMo-V2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index46
Knowledge benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
MMLU Pro78.7%82.9%MiMo-V2.5
LegalBench (Vals AI)81.2%78.9%Claude Haiku 4.5
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%59.9%Claude Haiku 4.5
TaxEval (Vals AI)67.5%71.8%MiMo-V2.5
MortgageTax (Vals AI)62.2%59.3%Claude Haiku 4.5
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%31.9%Claude Haiku 4.5
SimpleQA Verified13.2%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: science14061440MiMo-V2.5
LMArena Text: medicine and healthcare13941432MiMo-V2.5
LMArena Text: legal and government14001425MiMo-V2.5
LMArena Text: business and finance14001432MiMo-V2.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
Design Arena: websites11221266MiMo-V2.5
Design Arena: UI components11001257MiMo-V2.5
Design Arena: game dev10971249MiMo-V2.5
Design Arena: data viz11241249MiMo-V2.5
Design Arena: 3D10721216MiMo-V2.5
Design Arena: all code categories11151260MiMo-V2.5
Design Arena: SVG10251178MiMo-V2.5
Design Arena: ASCII art11391141MiMo-V2.5
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index317
General benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-V2.5Leader
LiveBench data analysis59.3%Not measuredOnly Claude Haiku 4.5 measured
Public Benefits Bench (Vals AI)54.3%Not measuredOnly Claude Haiku 4.5 measured
SAGE (Vals AI)31.8%43.3%MiMo-V2.5
MedScribe (Vals AI)85.2%72.2%Claude Haiku 4.5
Vals Multimodal Index42.9%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
DTBench73.6%Not measuredOnly Claude Haiku 4.5 measured
LMCA30.9%Not measuredOnly Claude Haiku 4.5 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971428MiMo-V2.5
LMArena Text: instruction following14141435MiMo-V2.5
LMArena Text: creative writing13711393MiMo-V2.5
LMArena VisionNot measured1247Only MiMo-V2.5 measured
LMArena Text: English14141447MiMo-V2.5
LMArena Text: non-English13771405MiMo-V2.5
LMArena Text: Chinese14181469MiMo-V2.5
LMArena Text: German13741421MiMo-V2.5
LMArena Text: Japanese13381306Claude Haiku 4.5
LMArena Text: Korean13461361MiMo-V2.5
LMArena Text: French14111448MiMo-V2.5
LMArena Text: Spanish14211414Claude Haiku 4.5
LMArena Text: Russian13811396MiMo-V2.5
LMArena Text: Polish13431413MiMo-V2.5
LMArena Text: multi-turn14091445MiMo-V2.5
LMArena Text: longer queries14271445MiMo-V2.5
LMArena Text: writing and language13861409MiMo-V2.5
LMArena Text: entertainment and media13691399MiMo-V2.5
LMArena Vision: EnglishNot measured1259Only MiMo-V2.5 measured
LMArena Vision: ChineseNot measured1326Only MiMo-V2.5 measured
LMArena Vision: reading textNot measured1256Only MiMo-V2.5 measured
LMArena Vision: humorNot measured1226Only MiMo-V2.5 measured
LMArena Vision: recognizing thingsNot measured1189Only MiMo-V2.5 measured
LMArena Vision: creative writingNot measured1230Only MiMo-V2.5 measured
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 4.5 and MiMo-V2.5
BenchmarkClaude Haiku 4.5MiMo-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

Claude Haiku 4.5$0.0035Fits in one request
MiMo-V2.5$0.0002Fits in one request

MiMo-V2.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
MiMo-V2.5$0.0067Fits in one request

MiMo-V2.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
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 Claude Haiku 4.5 and MiMo-V2.5
SpecificationAnthropic Claude Haiku 4.5Xiaomi MiMo-V2.5
MakerAnthropicXiaomi
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025April 22, 2026
Context window200K1.05M
Input $/Mtok$1.00$0.119
Output $/Mtok$5.00$0.238
Coding index49.834.0
Independent measurements behind it31
Cost per solved task$0.56$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than MiMo-V2.5 for coding?

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 34.0 for MiMo-V2.5. Pick MiMo-V2.5 when output tokens cost 21.0x less, or when a solved task costs $0.01 against $0.56.

Which is cheaper, Claude Haiku 4.5 or MiMo-V2.5?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; MiMo-V2.5 costs $0.119 and $0.238. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and MiMo-V2.5 $0.01.

Which has the bigger context window, Claude Haiku 4.5 or MiMo-V2.5?

MiMo-V2.5, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs MiMo-V2.5 comparison based on?

62 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 4.5's coding index rests on 3 independent benchmarks 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