Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs MiniMax M3

MiniMax M3 leads Claude Haiku 4.5 on coding, 39.2 to 35.6 on the Vibe Coding Index, and MiniMax M3 costs 4.2x less per output token ($1.20 vs $5.00 per million). Updated October 22, 2026; 79 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace MiniMax M3
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
1
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
78
vs boards won of 79 shared

Claude Haiku 4.5 or MiniMax M3: which to pick

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5.

Pick Claude Haiku 4.5 for work measured by LiveBench browser, where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
79
Claude Haiku 4.5 only
19
MiniMax M3 only
38
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
Claude Haiku 4.5 35.6 from 4 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Agentic work, 18.6 points apart on average over 9 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against MiniMax M3 82.2%, 41.0 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against MiniMax M3 $1.20 per million output tokens, 4.2x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, MiniMax M3 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 4.5BarsMiniMax M3Ties
Coding012
Intelligence02
Agentic work18
Reasoning08
Math03
Knowledge010
Web design09
General026
All shared boards178
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
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%70.9%MiniMax M3
LMArena WebDev13301482MiniMax M3
AA Coding Index43.958.6MiniMax M3
LiveCodeBench (Vals AI)41.2%82.2%MiniMax M3
SWE-bench Verified (Vals AI)66.6%75.0%MiniMax M3
Terminal-Bench 4 (Vals AI)Not measured1.0%Only MiniMax M3 measured
Vibe Code Bench (Vals AI)11.4%47.6%MiniMax M3
Code migration (Vals AI)7.5%19.9%MiniMax M3
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 2.1 (Vals AI)43.8%53.6%MiniMax M3
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)Not measured65.0%Only MiniMax M3 measured
SciCodeNot measured47.1%Only MiniMax M3 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured14.7%Only MiniMax M3 measured
WeirdML45.4%Not measuredOnly Claude Haiku 4.5 measured
ALE-BenchNot measured640.0Only MiniMax M3 measured
LMArena Text: coding14541470MiniMax M3
LMArena Text: software and IT14391466MiniMax M3
LMArena WebDev: React13261478MiniMax M3
LMArena WebDev: HTML13181455MiniMax M3
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
AA Intelligence Index16.929.2MiniMax M3
Epoch Capabilities Index142.2146.9MiniMax M3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index18
Agentic work benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
AA Agentic Index8.029.5MiniMax M3
Design Arena: agents building web appsNot measured1200Only MiniMax M3 measured
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile appsNot measured1169Only MiniMax M3 measured
Design Arena: agents building Android appsNot measured1158Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1159Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1120Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1178Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1042Only MiniMax M3 measured
LiveBench research42.2%68.0%MiniMax M3
LiveBench browser40.0%8.0%Claude Haiku 4.5
LiveBench long agentic11.1%12.4%MiniMax M3
Finance Agent (Vals AI)31.0%48.3%MiniMax M3
Tax Agent Bench (Vals AI)5.9%20.6%MiniMax M3
Legal Research Bench (Vals AI)10.6%29.8%MiniMax M3
Excel Modeling Benchmark (Vals AI)22.7%47.8%MiniMax M3
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-AgentsNot measured37.7%Only MiniMax M3 measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459$2,158MiniMax M3
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
MCP Atlas40.2%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
GPQA Diamond72.2%92.7%MiniMax M3
LiveBench reasoning61.7%74.5%MiniMax M3
MMMU Pro (Vals AI)46.1%81.2%MiniMax M3
GPQA Diamond (Artificial Analysis run)Not measured92.9%Only MiniMax M3 measured
Humanity's Last Exam (Artificial Analysis run)Not measured39.0%Only MiniMax M3 measured
GPQA Diamond (Epoch AI run)71.2%90.9%MiniMax M3
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzles8.0%13.0%MiniMax M3
Mystery game puzzlesNot measured8.0%Only MiniMax M3 measured
LMArena Text: hard prompts14211447MiniMax M3
LMArena Text: expert14431461MiniMax M3
LMArena Text: hard prompts in English14351455MiniMax M3
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
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%71.1%MiniMax M3
ProofBenchNot measured18.0%Only MiniMax M3 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981429MiniMax M3
LMArena Text: mathematical work14301448MiniMax M3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
Knowledge benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
MMLU Pro78.7%84.2%MiniMax M3
LegalBench (Vals AI)81.2%85.4%MiniMax M3
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%68.1%MiniMax M3
TaxEval (Vals AI)67.5%72.7%MiniMax M3
MortgageTax (Vals AI)62.2%68.4%MiniMax M3
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%46.3%MiniMax M3
SimpleQA Verified13.2%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: science14061452MiniMax M3
LMArena Text: medicine and healthcare13941441MiniMax M3
LMArena Text: legal and government14001437MiniMax M3
LMArena Text: business and finance14001434MiniMax M3
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index09
Web design benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
Design Arena: websites11221257MiniMax M3
Design Arena: UI components10971243MiniMax M3
Design Arena: game dev10961210MiniMax M3
Design Arena: data viz11241236MiniMax M3
Design Arena: 3D10711208MiniMax M3
Design Arena: all code categories11141246MiniMax M3
Design Arena: SVG10251160MiniMax M3
Design Arena: ASCII art11401161MiniMax M3
LiveBench design59.9%66.2%MiniMax M3
GeneralLike-for-likePublic boards, shown as published, kept out of the index026
General benchmarks for Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
LiveBench data analysis59.3%76.2%MiniMax M3
Public Benefits Bench (Vals AI)54.3%64.1%MiniMax M3
SAGE (Vals AI)31.8%50.6%MiniMax M3
MedScribe (Vals AI)85.2%87.3%MiniMax M3
Vals Multimodal Index42.9%60.0%MiniMax M3
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)Not measured83.0%Only MiniMax M3 measured
DTBench73.6%78.9%MiniMax M3
LMCA30.9%33.7%MiniMax M3
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971433MiniMax M3
LMArena Text: instruction following14141433MiniMax M3
LMArena Text: creative writing13711404MiniMax M3
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: English14141443MiniMax M3
LMArena Text: non-English13771420MiniMax M3
LMArena Text: Chinese14181466MiniMax M3
LMArena Text: German13741428MiniMax M3
LMArena Text: Japanese13381380MiniMax M3
LMArena Text: Korean13461373MiniMax M3
LMArena Text: French14111444MiniMax M3
LMArena Text: Spanish14211433MiniMax M3
LMArena Text: Russian13811426MiniMax M3
LMArena Text: Polish13431423MiniMax M3
LMArena Text: multi-turn14091443MiniMax M3
LMArena Text: longer queries14271446MiniMax M3
LMArena Text: writing and language13861419MiniMax M3
LMArena Text: entertainment and media13691403MiniMax M3
LMArena Vision: EnglishNot measured1263Only MiniMax M3 measured
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading textNot measured1259Only MiniMax M3 measured
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writingNot measured1234Only MiniMax M3 measured
LMArena Document14201435MiniMax M3
MultiChallenge50.5%Not measuredOnly Claude Haiku 4.5 measured
EQ-Bench 410641150MiniMax M3
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 Claude Haiku 4.5 and MiniMax M3
BenchmarkClaude Haiku 4.5MiniMax M3Leader
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
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
MiniMax M3$0.072Fits in one request

MiniMax M3 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 MiniMax M3
SpecificationAnthropic Claude Haiku 4.5MiniMax M3
MakerAnthropicMiniMax
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025May 31, 2026
Context window200K1.05M
Input $/Mtok$1.00$0.30
Output $/Mtok$5.00$1.20
Coding index35.639.2
Independent measurements behind it46
Cost per solved task$0.56$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than MiniMax M3 for coding?

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for work measured by LiveBench browser, where it leads.

Which is cheaper, Claude Haiku 4.5 or MiniMax M3?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and MiniMax M3 $0.56.

Which has the bigger context window, Claude Haiku 4.5 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs MiniMax M3 comparison based on?

79 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and MiniMax M3's on 6. 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/claude-haiku-4-5-vs-minimax-minimax-m3" title="Claude Haiku 4.5 vs MiniMax M3, 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/claude-haiku-4-5-vs-minimax-minimax-m3">LLMBenchmark.ai, Claude Haiku 4.5 vs MiniMax M3</a></p>