LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs MiniMax M3

Updated October 21, 2026. 110 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5 Replace MiniMax M3
Claude Sonnet 5Anthropic
Coding
63.5
Overall
38.2
Output $/M
$10.00
99
MiniMax M3MiniMax
Coding
57.8
Overall
29.2
Output $/M
$1.20
11
vs boards won of 110 shared

Decision reading

Pick Claude Sonnet 5 for coding: it scores 63.5 on the Vibe Coding Index against 57.8 for MiniMax M3.

Pick MiniMax M3 when output tokens cost 8.3x less, or when a solved task costs $0.56 against $1.87.

Model AClaude Sonnet 5Anthropic63.5/1002 independent benchmarks$1.87 per solved taskModel BMiniMax M3MiniMax57.8/1002 independent benchmarks$0.56 per solved task
Shared results
110
Claude Sonnet 5 only
10
MiniMax M3 only
6
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 Sonnet 5 63.5 from 2 benchmarks, MiniMax M3 57.8 from 2 benchmarks.
Widest category
Math, 23.6 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: Claude Sonnet 5 72.0% against MiniMax M3 8.0%, 64.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against MiniMax M3 $1.20 per million output tokens, 8.3x apart.
Context window
Claude Sonnet 5 takes 1M 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 Sonnet 5BarsMiniMax M3Ties
Coding191
Intelligence20
Agentic work171
Reasoning113
Math40
Knowledge82
Web design90
General294
All shared boards9911
CodingLike-for-likeFour of these boards feed the Vibe Coding Index191
Coding benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
LiveBench coding74.7%70.9%Claude Sonnet 5
LMArena WebDev15401482Claude Sonnet 5
AA Coding Index71.558.6Claude Sonnet 5
LiveCodeBench (Vals AI)82.4%82.2%Claude Sonnet 5
SWE-bench Verified (Vals AI)79.6%75.0%Claude Sonnet 5
Terminal-Bench 4 (Vals AI)10.6%1.0%Claude Sonnet 5
Vibe Code Bench (Vals AI)81.3%47.6%Claude Sonnet 5
Code migration (Vals AI)44.4%19.9%Claude Sonnet 5
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Sonnet 5 measured
IOI (Vals AI)45.0%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)74.5%53.6%Claude Sonnet 5
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)13.8%9.2%Claude Sonnet 5
SkillsBench (Vals AI)46.5%51.5%MiniMax M3
CyberBench (Vals AI)70.3%65.0%Claude Sonnet 5
SciCode54.3%47.1%Claude Sonnet 5
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode42.7%14.7%Claude Sonnet 5
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML68.8%Not measuredOnly Claude Sonnet 5 measured
ALE-Bench1463.1640.0Claude Sonnet 5
LMArena Text: coding14831470Claude Sonnet 5
LMArena Text: software and IT14741466Claude Sonnet 5
LMArena WebDev: React15411478Claude Sonnet 5
LMArena WebDev: HTML15271455Claude Sonnet 5
LMArena WebDev: from an image15401470Claude Sonnet 5
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
AA Intelligence Index38.229.2Claude Sonnet 5
Epoch Capabilities Index156.9146.9Claude Sonnet 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index171
Agentic work benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
AA Agentic Index43.629.5Claude Sonnet 5
Design Arena: agents building web apps12451200Claude Sonnet 5
Design Arena: agents building full-stack apps12491197Claude Sonnet 5
Design Arena: agents building mobile apps12151169Claude Sonnet 5
Design Arena: agents building Android apps12311164Claude Sonnet 5
Design Arena: agents building Godot games1225Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building games12271158Claude Sonnet 5
Design Arena: HTML slides12181180Claude Sonnet 5
Design Arena: PowerPoint slides12161205Claude Sonnet 5
Design Arena: spreadsheets10041021MiniMax M3
LiveBench research82.8%68.0%Claude Sonnet 5
LiveBench browser72.0%8.0%Claude Sonnet 5
LiveBench long agentic39.0%12.4%Claude Sonnet 5
SREBench (Vals AI)0.4%Not measuredOnly Claude Sonnet 5 measured
Finance Agent (Vals AI)53.9%48.3%Claude Sonnet 5
Tax Agent Bench (Vals AI)29.4%20.6%Claude Sonnet 5
Legal Research Bench (Vals AI)41.8%29.8%Claude Sonnet 5
Excel Modeling Benchmark (Vals AI)66.3%47.8%Claude Sonnet 5
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Claude Sonnet 5 measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-Agents54.5%37.7%Claude Sonnet 5
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2$6,378$2,158Claude Sonnet 5
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index113
Reasoning benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
GPQA Diamond88.9%92.7%MiniMax M3
LiveBench reasoning88.7%74.5%Claude Sonnet 5
MMMU Pro (Vals AI)83.0%81.2%Claude Sonnet 5
GPQA Diamond (Artificial Analysis run)91.1%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)41.3%39.0%Claude Sonnet 5
GPQA Diamond (Epoch AI run)90.5%90.9%MiniMax M3
SimpleBench60.6%45.8%Claude Sonnet 5
Chess puzzles45.0%13.0%Claude Sonnet 5
Mystery game puzzles35.0%8.0%Claude Sonnet 5
LMArena Text: hard prompts14611447Claude Sonnet 5
LMArena Text: expert14891461Claude Sonnet 5
LMArena Text: hard prompts in English14641455Claude Sonnet 5
LMArena Vision: diagrams12931266Claude Sonnet 5
LMArena Vision: homework13111268Claude Sonnet 5
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
OTIS Mock AIME94.7%71.1%Claude Sonnet 5
FrontierMath, tiers 1 to 365.6%Not measuredOnly Claude Sonnet 5 measured
FrontierMath, tier 429.3%Not measuredOnly Claude Sonnet 5 measured
ProofBench77.0%18.0%Claude Sonnet 5
LMArena Text: math14671429Claude Sonnet 5
LMArena Text: mathematical work14811448Claude Sonnet 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
Knowledge benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
MMLU Pro87.5%84.2%Claude Sonnet 5
LegalBench (Vals AI)83.9%85.4%MiniMax M3
CorpFin (Vals AI)67.0%68.1%MiniMax M3
TaxEval (Vals AI)75.6%72.7%Claude Sonnet 5
MortgageTax (Vals AI)70.0%68.4%Claude Sonnet 5
MedCode (Vals AI)47.5%46.3%Claude Sonnet 5
SimpleQA Verified33.7%Not measuredOnly Claude Sonnet 5 measured
LMArena Text: science14601452Claude Sonnet 5
LMArena Text: medicine and healthcare14421441Claude Sonnet 5
LMArena Text: legal and government14541437Claude Sonnet 5
LMArena Text: business and finance14361434Claude Sonnet 5
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
Design Arena: websites12741257Claude Sonnet 5
Design Arena: UI components12791246Claude Sonnet 5
Design Arena: game dev12781210Claude Sonnet 5
Design Arena: data viz12511235Claude Sonnet 5
Design Arena: 3D12611209Claude Sonnet 5
Design Arena: all code categories12761247Claude Sonnet 5
Design Arena: SVG11931161Claude Sonnet 5
Design Arena: ASCII art12071161Claude Sonnet 5
LiveBench design82.0%66.2%Claude Sonnet 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index294
General benchmarks for Claude Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 5MiniMax M3Leader
LiveBench data analysis71.7%76.2%MiniMax M3
Public Benefits Bench (Vals AI)66.0%64.1%Claude Sonnet 5
SAGE (Vals AI)48.9%50.6%MiniMax M3
MedScribe (Vals AI)76.0%87.3%MiniMax M3
Vals Multimodal Index68.8%60.0%Claude Sonnet 5
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)82.0%83.0%MiniMax M3
DTBench92.5%78.9%Claude Sonnet 5
LMCA50.0%33.7%Claude Sonnet 5
Surface Evolver Bench60.0%55.0%Claude Sonnet 5
LMArena Text14421433Claude Sonnet 5
LMArena Text: instruction following14521433Claude Sonnet 5
LMArena Text: creative writing14161404Claude Sonnet 5
LMArena Vision12731251Claude Sonnet 5
LMArena Text: English14501443Claude Sonnet 5
LMArena Text: non-English14311420Claude Sonnet 5
LMArena Text: Chinese14781466Claude Sonnet 5
LMArena Text: German14421428Claude Sonnet 5
LMArena Text: Japanese14221380Claude Sonnet 5
LMArena Text: Korean14121373Claude Sonnet 5
LMArena Text: French14631444Claude Sonnet 5
LMArena Text: Spanish14381433Claude Sonnet 5
LMArena Text: Russian14501426Claude Sonnet 5
LMArena Text: Polish14251423Claude Sonnet 5
LMArena Text: multi-turn14531443Claude Sonnet 5
LMArena Text: longer queries14621446Claude Sonnet 5
LMArena Text: writing and language14361419Claude Sonnet 5
LMArena Text: entertainment and media14111403Claude Sonnet 5
LMArena Vision: English12751263Claude Sonnet 5
LMArena Vision: Chinese13311311Claude Sonnet 5
LMArena Vision: reading text12881259Claude Sonnet 5
LMArena Vision: humor12611235Claude Sonnet 5
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writing12461234Claude Sonnet 5
LMArena Document14661435Claude Sonnet 5
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 Sonnet 5 and MiniMax M3
BenchmarkClaude Sonnet 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 Sonnet 5$0.0070Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits in one request
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 Sonnet 5 and MiniMax M3
SpecificationAnthropic Claude Sonnet 5MiniMax M3
MakerAnthropicMiniMax
WeightsNo public weights listedOpen weights
ReleasedJune 30, 2026May 31, 2026
Context window1M1.05M
Input $/Mtok$2.00$0.30
Output $/Mtok$10.00$1.20
Coding index63.557.8
Independent measurements behind it22
Cost per solved task$1.87$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than MiniMax M3 for coding?

Pick Claude Sonnet 5 for coding: it scores 63.5 on the Vibe Coding Index against 57.8 for MiniMax M3. Pick MiniMax M3 when output tokens cost 8.3x less, or when a solved task costs $0.56 against $1.87.

Which is cheaper, Claude Sonnet 5 or MiniMax M3?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and MiniMax M3 $0.56.

Which has the bigger context window, Claude Sonnet 5 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5 vs MiniMax M3 comparison based on?

110 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5's coding index rests on 2 independent benchmarks and MiniMax M3's on 2. 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-sonnet-5-vs-minimax-minimax-m3" title="Claude Sonnet 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-sonnet-5-vs-minimax-minimax-m3">LLMBenchmark.ai, Claude Sonnet 5 vs MiniMax M3</a></p>