Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs MiniMax M3

Claude Opus 4.8 leads MiniMax M3 on coding, 65.0 to 39.2 on the Vibe Coding Index, and MiniMax M3 costs 20.8x less per output token ($1.20 vs $25.00 per million). Updated October 22, 2026; 110 benchmarks have a result for both.

Replace Claude Opus 4.8 Replace MiniMax M3
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
102
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
8
vs boards won of 110 shared

Claude Opus 4.8 or MiniMax M3: which to pick

Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 39.2 for MiniMax M3.

Pick MiniMax M3 for output tokens 20.8x cheaper ($1.20 vs $25.00 per million) and a lower cost per solved task ($0.56 against $2.17).

Model AClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
110
Claude Opus 4.8 only
20
MiniMax M3 only
6
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 Opus 4.8 65.0 from 6 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Math, 24.0 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: Claude Opus 4.8 96.0% against MiniMax M3 8.0%, 88.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against MiniMax M3 $1.20 per million output tokens, 20.8x apart.
Context window
Claude Opus 4.8 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 Opus 4.8BarsMiniMax M3Ties
Coding170
Intelligence20
Agentic work200
Reasoning122
Math40
Knowledge82
Web design90
General304
All shared boards1028
CodingLike-for-likeSix of these boards feed the Vibe Coding Index170
Coding benchmarks for Claude Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
LiveBench coding77.3%70.9%Claude Opus 4.8
LMArena WebDev15561482Claude Opus 4.8
AA Coding Index74.358.6Claude Opus 4.8
LiveCodeBench (Vals AI)87.8%82.2%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%75.0%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%1.0%Claude Opus 4.8
Vibe Code Bench (Vals AI)82.7%47.6%Claude Opus 4.8
Code migration (Vals AI)47.3%19.9%Claude Opus 4.8
ProgramBench (Vals AI)1.0%Not measuredOnly Claude Opus 4.8 measured
Terminal-Bench 2.1 (Vals AI)71.9%53.6%Claude Opus 4.8
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)59.2%51.5%Claude Opus 4.8
CyberBench (Vals AI)Not measured65.0%Only MiniMax M3 measured
SciCode54.4%47.1%Claude Opus 4.8
Terminal-Bench Hard (Artificial Analysis run)58.3%42.4%Claude Opus 4.8
FrontierCode46.5%14.7%Claude Opus 4.8
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%Not measuredOnly Claude Opus 4.8 measured
ALE-BenchNot measured640.0Only MiniMax M3 measured
LMArena Text: coding14901470Claude Opus 4.8
LMArena Text: software and IT14881466Claude Opus 4.8
LMArena WebDev: React15571478Claude Opus 4.8
LMArena WebDev: HTML15431455Claude Opus 4.8
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
SciCode12.3%Not measuredOnly Claude Opus 4.8 measured
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 Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
AA Intelligence Index41.829.2Claude Opus 4.8
Epoch Capabilities Index159.0146.9Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index200
Agentic work benchmarks for Claude Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
AA Agentic Index41.929.5Claude Opus 4.8
Design Arena: agents building web apps12331200Claude Opus 4.8
Design Arena: agents building full-stack apps12491197Claude Opus 4.8
Design Arena: agents building mobile apps12221169Claude Opus 4.8
Design Arena: agents building Android apps12331159Claude Opus 4.8
Design Arena: agents building Godot games1231Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building games12391158Claude Opus 4.8
Design Arena: HTML slides11711130Claude Opus 4.8
Design Arena: PowerPoint slides12021181Claude Opus 4.8
Design Arena: spreadsheets13031028Claude Opus 4.8
LiveBench research81.8%68.0%Claude Opus 4.8
LiveBench browser96.0%8.0%Claude Opus 4.8
LiveBench long agentic48.3%12.4%Claude Opus 4.8
Finance Agent (Vals AI)53.9%48.3%Claude Opus 4.8
Tax Agent Bench (Vals AI)30.0%20.6%Claude Opus 4.8
Legal Research Bench (Vals AI)43.8%29.8%Claude Opus 4.8
Excel Modeling Benchmark (Vals AI)69.4%47.8%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Claude Opus 4.8 measured
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%88.9%Claude Opus 4.8
APEX-Agents48.9%37.7%Claude Opus 4.8
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%4.6%Claude Opus 4.8
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
Vending-Bench 2$5,787$2,158Claude Opus 4.8
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index122
Reasoning benchmarks for Claude Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
GPQA Diamond92.4%92.7%MiniMax M3
LiveBench reasoning89.2%74.5%Claude Opus 4.8
MMMU Pro (Vals AI)86.6%81.2%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)92.0%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)48.7%39.0%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%90.9%Claude Opus 4.8
ARC-AGI92.5%Not measuredOnly Claude Opus 4.8 measured
ARC-AGI-272.1%Not measuredOnly Claude Opus 4.8 measured
SimpleBench64.8%45.8%Claude Opus 4.8
Chess puzzles52.0%13.0%Claude Opus 4.8
Mystery game puzzles36.0%8.0%Claude Opus 4.8
EBR-bench28.6%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: hard prompts14821447Claude Opus 4.8
LMArena Text: expert15031461Claude Opus 4.8
LMArena Text: hard prompts in English14871455Claude Opus 4.8
LMArena Vision: diagrams13151266Claude Opus 4.8
LMArena Vision: homework13371268Claude Opus 4.8
Kagi LLM Benchmark88.8%Not measuredOnly Claude Opus 4.8 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 Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
OTIS Mock AIME98.3%71.1%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%Not measuredOnly Claude Opus 4.8 measured
FrontierMath, tier 456.1%Not measuredOnly Claude Opus 4.8 measured
ProofBench69.0%18.0%Claude Opus 4.8
LMArena Text: math14861429Claude Opus 4.8
LMArena Text: mathematical work14971448Claude Opus 4.8
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 Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
MMLU Pro89.6%84.2%Claude Opus 4.8
LegalBench (Vals AI)83.6%85.4%MiniMax M3
CorpFin (Vals AI)66.7%68.1%MiniMax M3
TaxEval (Vals AI)75.6%72.7%Claude Opus 4.8
MortgageTax (Vals AI)69.9%68.4%Claude Opus 4.8
MedCode (Vals AI)53.2%46.3%Claude Opus 4.8
SimpleQA Verified53.0%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: science14771452Claude Opus 4.8
LMArena Text: medicine and healthcare14641441Claude Opus 4.8
LMArena Text: legal and government14771437Claude Opus 4.8
LMArena Text: business and finance14581434Claude Opus 4.8
FACTS Benchmark Suite53.5%Not measuredOnly Claude Opus 4.8 measured
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 Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
Design Arena: websites12581257Claude Opus 4.8
Design Arena: UI components12551242Claude Opus 4.8
Design Arena: game dev12641210Claude Opus 4.8
Design Arena: data viz12401236Claude Opus 4.8
Design Arena: 3D12221208Claude Opus 4.8
Design Arena: all code categories12551247Claude Opus 4.8
Design Arena: SVG11951161Claude Opus 4.8
Design Arena: ASCII art12771161Claude Opus 4.8
LiveBench design78.8%66.2%Claude Opus 4.8
GeneralLike-for-likePublic boards, shown as published, kept out of the index304
General benchmarks for Claude Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax M3Leader
LiveBench data analysis66.0%76.2%MiniMax M3
Public Benefits Bench (Vals AI)68.1%64.1%Claude Opus 4.8
SAGE (Vals AI)54.8%50.6%Claude Opus 4.8
MedScribe (Vals AI)85.8%87.3%MiniMax M3
Vals Multimodal Index70.9%60.0%Claude Opus 4.8
IFBench62.2%82.9%MiniMax M3
Long context reasoning (AA-LCR)77.7%83.0%MiniMax M3
DTBench94.9%78.9%Claude Opus 4.8
LMCA57.5%33.7%Claude Opus 4.8
Surface Evolver Bench87.5%55.0%Claude Opus 4.8
Furniture assembly42.5%Not measuredOnly Claude Opus 4.8 measured
LMArena Text14611433Claude Opus 4.8
LMArena Text: instruction following14761433Claude Opus 4.8
LMArena Text: creative writing14541404Claude Opus 4.8
LMArena Vision12941251Claude Opus 4.8
LMArena Text: English14681443Claude Opus 4.8
LMArena Text: non-English14501420Claude Opus 4.8
LMArena Text: Chinese15061466Claude Opus 4.8
LMArena Text: German14721428Claude Opus 4.8
LMArena Text: Japanese14421380Claude Opus 4.8
LMArena Text: Korean14311373Claude Opus 4.8
LMArena Text: French14811444Claude Opus 4.8
LMArena Text: Spanish14651433Claude Opus 4.8
LMArena Text: Russian14741426Claude Opus 4.8
LMArena Text: Polish14591423Claude Opus 4.8
LMArena Text: multi-turn14761443Claude Opus 4.8
LMArena Text: longer queries14831446Claude Opus 4.8
LMArena Text: writing and language14611419Claude Opus 4.8
LMArena Text: entertainment and media14401403Claude Opus 4.8
LMArena Vision: English12931263Claude Opus 4.8
LMArena Vision: Chinese13461311Claude Opus 4.8
LMArena Vision: reading text13031259Claude Opus 4.8
LMArena Vision: humor12821235Claude Opus 4.8
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writing13011234Claude Opus 4.8
LMArena Document14751435Claude Opus 4.8
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 Opus 4.8 and MiniMax M3
BenchmarkClaude Opus 4.8MiniMax 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 Opus 4.8$0.018Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits 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 Opus 4.8 and MiniMax M3
SpecificationAnthropic Claude Opus 4.8MiniMax M3
MakerAnthropicMiniMax
WeightsNo public weights listedOpen weights
ReleasedMay 27, 2026May 31, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.30
Output $/Mtok$25.00$1.20
Coding index65.039.2
Independent measurements behind it66
Cost per solved task$2.17$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than MiniMax M3 for coding?

Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 39.2 for MiniMax M3. Pick MiniMax M3 for output tokens 20.8x cheaper ($1.20 vs $25.00 per million) and a lower cost per solved task ($0.56 against $2.17).

Which is cheaper, Claude Opus 4.8 or MiniMax M3?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and MiniMax M3 $0.56.

Which has the bigger context window, Claude Opus 4.8 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 4.8 vs MiniMax M3 comparison based on?

110 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.8'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-opus-4-8-vs-minimax-minimax-m3" title="Claude Opus 4.8 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-opus-4-8-vs-minimax-minimax-m3">LLMBenchmark.ai, Claude Opus 4.8 vs MiniMax M3</a></p>