Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs MiniMax M3

Claude Fable 5 leads MiniMax M3 on coding, 79.3 to 39.2 on the Vibe Coding Index, and MiniMax M3 costs 41.7x less per output token ($1.20 vs $50.00 per million). Updated October 22, 2026; 109 benchmarks have a result for both.

Replace Claude Fable 5 Replace MiniMax M3
Claude Fable 5Anthropic
Coding
79.3
Overall
79.0
Output $/M
$50.00
105
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
4
vs boards won of 109 shared

Claude Fable 5 or MiniMax M3: which to pick

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 39.2 for MiniMax M3.

Pick MiniMax M3 for output tokens 41.7x cheaper ($1.20 vs $50.00 per million) and a lower cost per solved task ($0.56 against $2.16).

Model AClaude Fable 5Anthropic79.3/1006 independent benchmarks$2.16 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
109
Claude Fable 5 only
18
MiniMax M3 only
7
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 Fable 5 79.3 from 6 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Math, 32.9 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: Claude Fable 5 92.0% against MiniMax M3 8.0%, 84.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against MiniMax M3 $1.20 per million output tokens, 41.7x apart.
Context window
Claude Fable 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 Fable 5BarsMiniMax M3Ties
Coding180
Intelligence20
Agentic work180
Reasoning122
Math40
Knowledge100
Web design90
General322
All shared boards1054
CodingLike-for-likeSix of these boards feed the Vibe Coding Index180
Coding benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
LiveBench coding98.3%70.9%Claude Fable 5
LMArena WebDev16241482Claude Fable 5
AA Coding Index76.558.6Claude Fable 5
LiveCodeBench (Vals AI)89.8%82.2%Claude Fable 5
SWE-bench Verified (Vals AI)95.0%75.0%Claude Fable 5
Terminal-Bench 4 (Vals AI)41.4%1.0%Claude Fable 5
Vibe Code Bench (Vals AI)90.3%47.6%Claude Fable 5
Code migration (Vals AI)55.1%19.9%Claude Fable 5
ProgramBench (Vals AI)2.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 2.1 (Vals AI)80.5%53.6%Claude Fable 5
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
SciCode61.0%47.1%Claude Fable 5
Terminal-Bench Hard (Artificial Analysis run)62.9%42.4%Claude Fable 5
FrontierCode53.5%14.7%Claude Fable 5
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%Not measuredOnly Claude Fable 5 measured
WeirdML91.9%Not measuredOnly Claude Fable 5 measured
MirrorCode63.9%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.3640.0Claude Fable 5
LMArena Text: coding15181470Claude Fable 5
LMArena Text: software and IT15131466Claude Fable 5
LMArena WebDev: React16311478Claude Fable 5
LMArena WebDev: HTML16511455Claude Fable 5
LMArena WebDev: from an image16231470Claude Fable 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 Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
AA Intelligence Index49.629.2Claude Fable 5
Epoch Capabilities Index163.4146.9Claude Fable 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index180
Agentic work benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
AA Agentic Index50.729.5Claude Fable 5
Design Arena: agents building web apps12611200Claude Fable 5
Design Arena: agents building full-stack apps12801197Claude Fable 5
Design Arena: agents building mobile apps12631169Claude Fable 5
Design Arena: agents building Android apps12841159Claude Fable 5
Design Arena: agents building Godot games1292Not measuredOnly Claude Fable 5 measured
Design Arena: agents building games12851159Claude Fable 5
Design Arena: HTML slides12271130Claude Fable 5
Design Arena: PowerPoint slides12721181Claude Fable 5
Design Arena: spreadsheetsNot measured1039Only MiniMax M3 measured
LiveBench research86.9%68.0%Claude Fable 5
LiveBench browser92.0%8.0%Claude Fable 5
LiveBench long agentic53.2%12.4%Claude Fable 5
Finance Agent (Vals AI)56.3%48.3%Claude Fable 5
Tax Agent Bench (Vals AI)38.3%20.6%Claude Fable 5
Legal Research Bench (Vals AI)49.5%29.8%Claude Fable 5
Excel Modeling Benchmark (Vals AI)73.7%47.8%Claude Fable 5
Terminal-Bench-Science (Vals AI)15.7%Not measuredOnly Claude Fable 5 measured
τ²-Bench Telecom98.5%88.9%Claude Fable 5
APEX-Agents63.6%37.7%Claude Fable 5
Remote Labor Index16.1%Not measuredOnly Claude Fable 5 measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
PostTrainBench41.8%Not measuredOnly Claude Fable 5 measured
Vending-Bench 2$5,680$2,158Claude Fable 5
LMArena Search1229Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index122
Reasoning benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
GPQA Diamond93.2%92.7%Claude Fable 5
LiveBench reasoning89.7%74.5%Claude Fable 5
MMMU Pro (Vals AI)89.3%81.2%Claude Fable 5
GPQA Diamond (Artificial Analysis run)92.6%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)55.5%39.0%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%90.9%MiniMax M3
ARC-AGI98.5%Not measuredOnly Claude Fable 5 measured
ARC-AGI-289.2%Not measuredOnly Claude Fable 5 measured
SimpleBench81.9%45.8%Claude Fable 5
Chess puzzles47.0%13.0%Claude Fable 5
Mystery game puzzles52.0%8.0%Claude Fable 5
EBR-bench39.5%Not measuredOnly Claude Fable 5 measured
LMArena Text: hard prompts15071447Claude Fable 5
LMArena Text: expert15341461Claude Fable 5
LMArena Text: hard prompts in English15091455Claude Fable 5
LMArena Vision: diagrams13571266Claude Fable 5
LMArena Vision: homework13611268Claude Fable 5
Kagi LLM Benchmark91.4%Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
OTIS Mock AIME100.0%71.1%Claude Fable 5
FrontierMath, tiers 1 to 387.0%Not measuredOnly Claude Fable 5 measured
FrontierMath, tier 490.2%Not measuredOnly Claude Fable 5 measured
ProofBench95.0%18.0%Claude Fable 5
LMArena Text: math15161429Claude Fable 5
LMArena Text: mathematical work15151448Claude Fable 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
MMLU Pro91.5%84.2%Claude Fable 5
LegalBench (Vals AI)88.6%85.4%Claude Fable 5
CorpFin (Vals AI)71.8%68.1%Claude Fable 5
TaxEval (Vals AI)76.9%72.7%Claude Fable 5
MortgageTax (Vals AI)68.9%68.4%Claude Fable 5
MedCode (Vals AI)56.1%46.3%Claude Fable 5
SimpleQA Verified70.7%Not measuredOnly Claude Fable 5 measured
LMArena Text: science15061452Claude Fable 5
LMArena Text: medicine and healthcare14801441Claude Fable 5
LMArena Text: legal and government14981437Claude Fable 5
LMArena Text: business and finance14801434Claude Fable 5
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
Design Arena: websites12951257Claude Fable 5
Design Arena: UI components13161243Claude Fable 5
Design Arena: game dev13351211Claude Fable 5
Design Arena: data viz13051236Claude Fable 5
Design Arena: 3D13181208Claude Fable 5
Design Arena: all code categories13101246Claude Fable 5
Design Arena: SVG13011160Claude Fable 5
Design Arena: ASCII art13291161Claude Fable 5
LiveBench design84.7%66.2%Claude Fable 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index322
General benchmarks for Claude Fable 5 and MiniMax M3
BenchmarkClaude Fable 5MiniMax M3Leader
LiveBench data analysis80.5%76.2%Claude Fable 5
Public Benefits Bench (Vals AI)70.4%64.1%Claude Fable 5
SAGE (Vals AI)51.9%50.6%Claude Fable 5
MedScribe (Vals AI)88.5%87.3%Claude Fable 5
Vals Multimodal Index74.2%60.0%Claude Fable 5
IFBench63.5%82.9%MiniMax M3
Long context reasoning (AA-LCR)82.3%83.0%MiniMax M3
DTBench98.4%78.9%Claude Fable 5
LMCA61.2%33.7%Claude Fable 5
Surface Evolver Bench95.0%55.0%Claude Fable 5
Furniture assembly35.8%Not measuredOnly Claude Fable 5 measured
LMArena Text14911433Claude Fable 5
LMArena Text: instruction following15021433Claude Fable 5
LMArena Text: creative writing14941404Claude Fable 5
LMArena Vision13251251Claude Fable 5
LMArena Text: English14981443Claude Fable 5
LMArena Text: non-English14821420Claude Fable 5
LMArena Text: Chinese15431466Claude Fable 5
LMArena Text: German14861428Claude Fable 5
LMArena Text: Japanese15041380Claude Fable 5
LMArena Text: Korean14871373Claude Fable 5
LMArena Text: French15051444Claude Fable 5
LMArena Text: Spanish14981433Claude Fable 5
LMArena Text: Russian15031426Claude Fable 5
LMArena Text: Polish14941423Claude Fable 5
LMArena Text: multi-turn15041443Claude Fable 5
LMArena Text: longer queries15101446Claude Fable 5
LMArena Text: writing and language15011419Claude Fable 5
LMArena Text: entertainment and media14821403Claude Fable 5
LMArena Vision: English13231263Claude Fable 5
LMArena Vision: Chinese13731311Claude Fable 5
LMArena Vision: reading text13371259Claude Fable 5
LMArena Vision: humor13411235Claude Fable 5
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writing13381234Claude Fable 5
LMArena Document14961435Claude Fable 5
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 Fable 5 and MiniMax M3
BenchmarkClaude Fable 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 Fable 5$0.035Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits 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 Fable 5 and MiniMax M3
SpecificationAnthropic Claude Fable 5MiniMax M3
MakerAnthropicMiniMax
WeightsNo public weights listedOpen weights
ReleasedJune 9, 2026May 31, 2026
Context window1M1.05M
Input $/Mtok$10.00$0.30
Output $/Mtok$50.00$1.20
Coding index79.339.2
Independent measurements behind it66
Cost per solved task$2.16$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than MiniMax M3 for coding?

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 39.2 for MiniMax M3. Pick MiniMax M3 for output tokens 41.7x cheaper ($1.20 vs $50.00 per million) and a lower cost per solved task ($0.56 against $2.16).

Which is cheaper, Claude Fable 5 or MiniMax M3?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Fable 5 costs $2.16 and MiniMax M3 $0.56.

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

MiniMax M3, with 1.05M tokens against 1M.

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

109 benchmarks have a result for both models as of October 22, 2026. Claude Fable 5's coding index rests on 6 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-fable-5-vs-minimax-minimax-m3" title="Claude Fable 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-fable-5-vs-minimax-minimax-m3">LLMBenchmark.ai, Claude Fable 5 vs MiniMax M3</a></p>