LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs MiniMax M2.7

Updated October 21, 2026. 65 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 MiniMax M2.7
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
15
MiniMax M2.7MiniMax
Coding
28.4
Overall
22.8
Output $/M
$1.20
48
vs boards won of 65 shared, 2 tied

Decision reading

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 28.4 for MiniMax M2.7.

Pick MiniMax M2.7 when output tokens cost 4.2x less, or when the context window is larger, 205K against 200K tokens.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BMiniMax M2.7MiniMax28.4/1001 independent benchmark$0.64 per solved task
Shared results
65
Claude Haiku 4.5 only
29
MiniMax M2.7 only
9
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, MiniMax M2.7 28.4 from 1 benchmark.
Widest category
Web design, 12.6 points apart on average over 8 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against MiniMax M2.7 79.9%, 38.8 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against MiniMax M2.7 $1.20 per million output tokens, 4.2x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, MiniMax M2.7 205K.

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 M2.7Ties
Coding1121 tie
Intelligence02
Agentic work131 tie
Reasoning13
Math03
Knowledge19
Web design17
General109
All shared boards15482 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index112
Coding benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
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 WebDev13301399MiniMax M2.7
AA Coding Index43.952.6MiniMax M2.7
LiveCodeBench (Vals AI)41.2%79.9%MiniMax M2.7
SWE-bench Verified (Vals AI)66.6%73.8%MiniMax M2.7
Vibe Code Bench (Vals AI)11.4%11.9%MiniMax M2.7
Code migration (Vals AI)7.5%8.7%MiniMax M2.7
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)43.8%48.7%MiniMax M2.7
SciCodeNot measured50.1%Only MiniMax M2.7 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured39.4%Only MiniMax M2.7 measured
Terminal-Bench35.5%45.1%MiniMax M2.7
WeirdML45.4%37.0%Claude Haiku 4.5
ALE-BenchNot measured599.3Only MiniMax M2.7 measured
LMArena Text: coding14541454MiniMax M2.7
LMArena Text: software and IT14391446MiniMax M2.7
LMArena WebDev: React13261388MiniMax M2.7
LMArena WebDev: HTML13181401MiniMax M2.7
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
AA Intelligence Index16.922.8MiniMax M2.7
Epoch Capabilities Index142.2145.8MiniMax M2.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index13
Agentic work benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
AA Agentic Index8.015.3MiniMax M2.7
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%27.9%Claude Haiku 4.5
Tax Agent Bench (Vals AI)5.9%6.9%MiniMax M2.7
Legal Research Bench (Vals AI)10.6%10.6%Tie
Excel Modeling Benchmark (Vals AI)22.7%28.4%MiniMax M2.7
τ²-Bench TelecomNot measured84.8%Only MiniMax M2.7 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 index13
Reasoning benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
GPQA Diamond72.2%86.6%MiniMax M2.7
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%Not measuredOnly Claude Haiku 4.5 measured
GPQA Diamond (Artificial Analysis run)Not measured87.4%Only MiniMax M2.7 measured
Humanity's Last Exam (Artificial Analysis run)Not measured29.6%Only MiniMax M2.7 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 prompts14211422MiniMax M2.7
LMArena Text: expert14431443Claude Haiku 4.5
LMArena Text: hard prompts in English14351441MiniMax M2.7
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
AIME82.7%91.0%MiniMax M2.7
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%Not measuredOnly Claude Haiku 4.5 measured
ProofBenchNot measured3.0%Only MiniMax M2.7 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981421MiniMax M2.7
LMArena Text: mathematical work14301437MiniMax M2.7
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
MMLU Pro78.7%80.4%MiniMax M2.7
LegalBench (Vals AI)81.2%84.0%MiniMax M2.7
CaseLaw (Vals AI)56.5%60.9%MiniMax M2.7
CorpFin (Vals AI)60.6%61.2%MiniMax M2.7
TaxEval (Vals AI)67.5%66.6%Claude Haiku 4.5
MortgageTax (Vals AI)62.2%Not measuredOnly Claude Haiku 4.5 measured
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%34.4%MiniMax M2.7
SimpleQA Verified13.2%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: science14061416MiniMax M2.7
LMArena Text: medicine and healthcare13941409MiniMax M2.7
LMArena Text: legal and government14001403MiniMax M2.7
LMArena Text: business and finance14001407MiniMax M2.7
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
Design Arena: websites11221243MiniMax M2.7
Design Arena: UI components11001210MiniMax M2.7
Design Arena: game dev10971210MiniMax M2.7
Design Arena: data viz11241233MiniMax M2.7
Design Arena: 3D10721195MiniMax M2.7
Design Arena: all code categories11151233MiniMax M2.7
Design Arena: SVG10251136MiniMax M2.7
Design Arena: ASCII art11391136Claude Haiku 4.5
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index109
General benchmarks for Claude Haiku 4.5 and MiniMax M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
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%Not measuredOnly Claude Haiku 4.5 measured
MedScribe (Vals AI)85.2%79.9%Claude Haiku 4.5
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
IFBenchNot measured75.7%Only MiniMax M2.7 measured
Long context reasoning (AA-LCR)Not measured78.3%Only MiniMax M2.7 measured
DTBench73.6%Not measuredOnly Claude Haiku 4.5 measured
LMCA30.9%Not measuredOnly Claude Haiku 4.5 measured
ExploitBench13.7%13.3%Claude Haiku 4.5
LMArena Text13971405MiniMax M2.7
LMArena Text: instruction following14141405Claude Haiku 4.5
LMArena Text: creative writing13711354Claude Haiku 4.5
LMArena Text: English14141426MiniMax M2.7
LMArena Text: non-English13771382MiniMax M2.7
LMArena Text: Chinese14181442MiniMax M2.7
LMArena Text: German13741398MiniMax M2.7
LMArena Text: Japanese13381260Claude Haiku 4.5
LMArena Text: Korean13461314Claude Haiku 4.5
LMArena Text: French14111424MiniMax M2.7
LMArena Text: Spanish14211402Claude Haiku 4.5
LMArena Text: Russian13811383MiniMax M2.7
LMArena Text: Polish13431387MiniMax M2.7
LMArena Text: multi-turn14091412MiniMax M2.7
LMArena Text: longer queries14271418Claude Haiku 4.5
LMArena Text: writing and language13861376Claude Haiku 4.5
LMArena Text: entertainment and media13691360Claude Haiku 4.5
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 18 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 M2.7
BenchmarkClaude Haiku 4.5MiniMax M2.7Leader
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 M2.7$0.0009Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
MiniMax M2.7$0.019Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
MiniMax M2.7$0.072Exceeds the context window

MiniMax M2.7 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 M2.7
SpecificationAnthropic Claude Haiku 4.5MiniMax M2.7
MakerAnthropicMiniMax
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025March 18, 2026
Context window200K205K
Input $/Mtok$1.00$0.30
Output $/Mtok$5.00$1.20
Coding index49.828.4
Independent measurements behind it31
Cost per solved task$0.56$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than MiniMax M2.7 for coding?

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 28.4 for MiniMax M2.7. Pick MiniMax M2.7 when output tokens cost 4.2x less, or when the context window is larger, 205K against 200K tokens.

Which is cheaper, Claude Haiku 4.5 or MiniMax M2.7?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and MiniMax M2.7 $0.64.

Which has the bigger context window, Claude Haiku 4.5 or MiniMax M2.7?

MiniMax M2.7, with 205K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs MiniMax M2.7 comparison based on?

65 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 MiniMax M2.7's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next