LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 5.5 vs MiniMax M3

Updated October 21, 2026. 80 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5.5 Replace MiniMax M3
Claude Sonnet 5.5Anthropic
Coding
88.9
Overall
56.0
Output $/M
$10.00
77
MiniMax M3MiniMax
Coding
57.8
Overall
29.2
Output $/M
$1.20
3
vs boards won of 80 shared

Decision reading

Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 57.8 for MiniMax M3.

Pick MiniMax M3 when output tokens cost 8.3x less, or when the context window is larger, 1.05M against 1M tokens.

Model AClaude Sonnet 5.5Anthropic88.9/1002 independent benchmarksNo cost per solved taskModel BMiniMax M3MiniMax57.8/1002 independent benchmarks$0.56 per solved task
Shared results
80
Claude Sonnet 5.5 only
15
MiniMax M3 only
36
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 5.5 88.9 from 2 benchmarks, MiniMax M3 57.8 from 2 benchmarks.
Widest category
Math, 33.1 points apart on average over 4 shared benchmarks.
Widest single gap
ProofBench: Claude Sonnet 5.5 100.0% against MiniMax M3 18.0%, 82.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5.5 $10.00 against MiniMax M3 $1.20 per million output tokens, 8.3x apart.
Context window
Claude Sonnet 5.5 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 5.5BarsMiniMax M3Ties
Coding151
Intelligence20
Agentic work120
Reasoning100
Math40
Knowledge50
Web design70
General222
All shared boards773
CodingLike-for-likeFour of these boards feed the Vibe Coding Index151
Coding benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
LiveBench coding94.7%70.9%Claude Sonnet 5.5
LMArena WebDev17681482Claude Sonnet 5.5
AA Coding IndexNot measured58.6Only MiniMax M3 measured
LiveCodeBench (Vals AI)Not measured82.2%Only MiniMax M3 measured
SWE-bench Verified (Vals AI)Not measured75.0%Only MiniMax M3 measured
Terminal-Bench 4 (Vals AI)64.1%1.0%Claude Sonnet 5.5
Vibe Code Bench (Vals AI)92.4%47.6%Claude Sonnet 5.5
Code migration (Vals AI)69.8%19.9%Claude Sonnet 5.5
ProgramBench (Vals AI)6.5%Not measuredOnly Claude Sonnet 5.5 measured
IOI (Vals AI)83.1%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench 2.1 (Vals AI)83.2%53.6%Claude Sonnet 5.5
SWE-bench Multimodal (Vals AI)58.3%33.3%Claude Sonnet 5.5
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)59.6%65.0%MiniMax M3
SciCode61.0%47.1%Claude Sonnet 5.5
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode52.1%14.7%Claude Sonnet 5.5
FrontierSWE61.9%Not measuredOnly Claude Sonnet 5.5 measured
ALE-Bench1819.1640.0Claude Sonnet 5.5
LMArena Text: coding15131470Claude Sonnet 5.5
LMArena Text: software and IT15041466Claude Sonnet 5.5
LMArena WebDev: React18171478Claude Sonnet 5.5
LMArena WebDev: HTML17411455Claude Sonnet 5.5
LMArena WebDev: from an image17371470Claude Sonnet 5.5
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
AA Intelligence Index56.029.2Claude Sonnet 5.5
Epoch Capabilities Index166.2146.9Claude Sonnet 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index120
Agentic work benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
AA Agentic IndexNot measured29.5Only MiniMax M3 measured
Design Arena: agents building web apps13031200Claude Sonnet 5.5
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile apps12651169Claude Sonnet 5.5
Design Arena: agents building Android appsNot measured1164Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1158Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1180Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1205Only MiniMax M3 measured
Design Arena: spreadsheets12451021Claude Sonnet 5.5
LiveBench research83.6%68.0%Claude Sonnet 5.5
LiveBench browser84.0%8.0%Claude Sonnet 5.5
LiveBench long agentic78.8%12.4%Claude Sonnet 5.5
SREBench (Vals AI)30.1%Not measuredOnly Claude Sonnet 5.5 measured
Finance Agent (Vals AI)58.1%48.3%Claude Sonnet 5.5
Tax Agent Bench (Vals AI)42.0%20.6%Claude Sonnet 5.5
Legal Research Bench (Vals AI)48.1%29.8%Claude Sonnet 5.5
Harvey's Legal Agent Benchmark (Vals AI)10.4%Not measuredOnly Claude Sonnet 5.5 measured
Excel Modeling Benchmark (Vals AI)75.7%47.8%Claude Sonnet 5.5
BioMysteryBench (Vals AI)81.1%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench-Science (Vals AI)47.1%Not measuredOnly Claude Sonnet 5.5 measured
Vals Science Index59.1%Not measuredOnly Claude Sonnet 5.5 measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-Agents75.5%37.7%Claude Sonnet 5.5
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
SpireClimb1.3%Not measuredOnly Claude Sonnet 5.5 measured
Vending-Bench 2$11,165$2,158Claude Sonnet 5.5
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
GPQA DiamondNot measured92.7%Only MiniMax M3 measured
LiveBench reasoning91.6%74.5%Claude Sonnet 5.5
MysteryMechanism (Vals AI)49.1%Not measuredOnly Claude Sonnet 5.5 measured
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)Not measured92.9%Only MiniMax M3 measured
Humanity's Last Exam (Artificial Analysis run)55.0%39.0%Claude Sonnet 5.5
GPQA Diamond (Epoch AI run)95.6%90.9%Claude Sonnet 5.5
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzles59.0%13.0%Claude Sonnet 5.5
Mystery game puzzles65.0%8.0%Claude Sonnet 5.5
LMArena Text: hard prompts14941447Claude Sonnet 5.5
LMArena Text: expert15311461Claude Sonnet 5.5
LMArena Text: hard prompts in English15021455Claude Sonnet 5.5
LMArena Vision: diagrams13291266Claude Sonnet 5.5
LMArena Vision: homework13311268Claude Sonnet 5.5
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
OTIS Mock AIME100.0%71.1%Claude Sonnet 5.5
FrontierMath, tiers 1 to 388.8%Not measuredOnly Claude Sonnet 5.5 measured
FrontierMath, tier 480.5%Not measuredOnly Claude Sonnet 5.5 measured
ProofBench100.0%18.0%Claude Sonnet 5.5
LMArena Text: math14971429Claude Sonnet 5.5
LMArena Text: mathematical work15101448Claude Sonnet 5.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
MMLU ProNot measured84.2%Only MiniMax M3 measured
LegalBench (Vals AI)Not measured85.4%Only MiniMax M3 measured
CorpFin (Vals AI)Not measured68.1%Only MiniMax M3 measured
TaxEval (Vals AI)Not measured72.7%Only MiniMax M3 measured
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)52.9%46.3%Claude Sonnet 5.5
SimpleQA Verified46.5%Not measuredOnly Claude Sonnet 5.5 measured
LMArena Text: science14831452Claude Sonnet 5.5
LMArena Text: medicine and healthcare14641441Claude Sonnet 5.5
LMArena Text: legal and government14831437Claude Sonnet 5.5
LMArena Text: business and finance14681434Claude Sonnet 5.5
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
Design Arena: websites13261257Claude Sonnet 5.5
Design Arena: UI components13671246Claude Sonnet 5.5
Design Arena: game dev14691210Claude Sonnet 5.5
Design Arena: data viz13891235Claude Sonnet 5.5
Design Arena: 3D14581209Claude Sonnet 5.5
Design Arena: all code categories13641247Claude Sonnet 5.5
Design Arena: SVGNot measured1161Only MiniMax M3 measured
Design Arena: ASCII artNot measured1161Only MiniMax M3 measured
LiveBench design85.0%66.2%Claude Sonnet 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index222
General benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax M3Leader
Vals Index70.8%Not measuredOnly Claude Sonnet 5.5 measured
LiveBench data analysis59.5%76.2%MiniMax M3
Public Benefits Bench (Vals AI)67.2%64.1%Claude Sonnet 5.5
SAGE (Vals AI)51.8%50.6%Claude Sonnet 5.5
MedScribe (Vals AI)91.1%87.3%Claude Sonnet 5.5
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)82.7%83.0%MiniMax M3
DTBench97.3%78.9%Claude Sonnet 5.5
LMCA68.3%33.7%Claude Sonnet 5.5
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
Furniture assembly75.0%Not measuredOnly Claude Sonnet 5.5 measured
LMArena Text14731433Claude Sonnet 5.5
LMArena Text: instruction following14921433Claude Sonnet 5.5
LMArena Text: creative writing14671404Claude Sonnet 5.5
LMArena Vision12871251Claude Sonnet 5.5
LMArena Text: English14841443Claude Sonnet 5.5
LMArena Text: non-English14561420Claude Sonnet 5.5
LMArena Text: Chinese15351466Claude Sonnet 5.5
LMArena Text: GermanNot measured1428Only MiniMax M3 measured
LMArena Text: JapaneseNot measured1380Only MiniMax M3 measured
LMArena Text: KoreanNot measured1373Only MiniMax M3 measured
LMArena Text: French14991444Claude Sonnet 5.5
LMArena Text: Spanish14511433Claude Sonnet 5.5
LMArena Text: Russian14541426Claude Sonnet 5.5
LMArena Text: PolishNot measured1423Only MiniMax M3 measured
LMArena Text: multi-turn14651443Claude Sonnet 5.5
LMArena Text: longer queries14951446Claude Sonnet 5.5
LMArena Text: writing and language14741419Claude Sonnet 5.5
LMArena Text: entertainment and media14611403Claude Sonnet 5.5
LMArena Vision: English12891263Claude Sonnet 5.5
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading text12971259Claude Sonnet 5.5
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writing12421234Claude Sonnet 5.5
LMArena DocumentNot measured1435Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5.5 and MiniMax M3
BenchmarkClaude Sonnet 5.5MiniMax 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 5.5$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 5.5$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 5.5$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 5.5 and MiniMax M3
SpecificationAnthropic Claude Sonnet 5.5MiniMax M3
MakerAnthropicMiniMax
WeightsNo public weights listedOpen weights
ReleasedSeptember 28, 2026May 31, 2026
Context window1M1.05M
Input $/Mtok$2.00$0.30
Output $/Mtok$10.00$1.20
Coding index88.957.8
Independent measurements behind it22
Cost per solved taskNot computable$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5.5 better than MiniMax M3 for coding?

Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 57.8 for MiniMax M3. Pick MiniMax M3 when output tokens cost 8.3x less, or when the context window is larger, 1.05M against 1M tokens.

Which is cheaper, Claude Sonnet 5.5 or MiniMax M3?

Claude Sonnet 5.5 costs $2.00 per million input tokens and $10.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, Claude Sonnet 5.5 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5.5 vs MiniMax M3 comparison based on?

80 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5.5'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-5-5-vs-minimax-minimax-m3" title="Claude Sonnet 5.5 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-5-5-vs-minimax-minimax-m3">LLMBenchmark.ai, Claude Sonnet 5.5 vs MiniMax M3</a></p>