Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs GPT-5 Mini

Claude Opus 4.6 leads GPT-5 Mini on coding, 57.2 to 34.2 on the Vibe Coding Index, and GPT-5 Mini costs 12.5x less per output token ($2.00 vs $25.00 per million). Updated October 22, 2026; 90 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace GPT-5 Mini
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
84
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
6
vs boards won of 90 shared

Claude Opus 4.6 or GPT-5 Mini: which to pick

Pick Claude Opus 4.6 for coding: it scores 57.2 on the Vibe Coding Index against 34.2 for GPT-5 Mini.

Pick GPT-5 Mini for output tokens 12.5x cheaper ($2.00 vs $25.00 per million) and a lower cost per solved task ($0.08 against $1.56).

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved task
Shared results
90
Claude Opus 4.6 only
29
GPT-5 Mini only
13
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 4.6 57.2 from 4 benchmarks, GPT-5 Mini 34.2 from 2 benchmarks.
Widest category
Agentic work, 35.6 points apart on average over 2 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 4.6 69.2% against GPT-5 Mini 4.4%, 64.7 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against GPT-5 Mini $2.00 per million output tokens, 12.5x apart.
Context window
Claude Opus 4.6 takes 1M tokens, GPT-5 Mini 400K.

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 4.6BarsGPT-5 MiniTies
Coding91
Intelligence20
Agentic work20
Reasoning141
Math80
Knowledge122
Web design80
General292
All shared boards846
CodingLike-for-likeSix of these boards feed the Vibe Coding Index91
Coding benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
SWE-bench Verified75.6%59.8%Claude Opus 4.6
SWE-bench Multilingual72.0%39.7%Claude Opus 4.6
LMArena WebDev1547Not measuredOnly Claude Opus 4.6 measured
LiveCodeBench (Vals AI)84.7%86.6%GPT-5 Mini
SWE-bench Verified (Vals AI)78.2%60.8%Claude Opus 4.6
Vibe Code Bench (Vals AI)57.6%14.2%Claude Opus 4.6
LiveCodeBench (Artificial Analysis run)Not measured83.8%Only GPT-5 Mini measured
SciCodeNot measured39.0%Only GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)48.5%33.3%Claude Opus 4.6
Terminal-Bench79.8%34.8%Claude Opus 4.6
FrontierCode26.6%Not measuredOnly Claude Opus 4.6 measured
GSO-Bench41.2%Not measuredOnly Claude Opus 4.6 measured
WeirdML78.0%52.7%Claude Opus 4.6
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: coding15341406Claude Opus 4.6
LMArena Text: software and IT15271394Claude Opus 4.6
LMArena WebDev: React1539Not measuredOnly Claude Opus 4.6 measured
LMArena WebDev: HTML1559Not measuredOnly Claude Opus 4.6 measured
LMArena WebDev: from an image1543Not measuredOnly Claude Opus 4.6 measured
SWE Atlas: Codebase QnA33.3%Not measuredOnly Claude Opus 4.6 measured
SWE Atlas: Refactoring35.6%Not measuredOnly Claude Opus 4.6 measured
SWE Atlas: Test Writing36.7%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
AA Intelligence Index31.920.6Claude Opus 4.6
Epoch Capabilities Index155.7145.3Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
Design Arena: agents building web apps1206Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building full-stack apps1220Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building mobile apps1207Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building Android apps1197Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building games1213Not measuredOnly Claude Opus 4.6 measured
τ²-Bench Telecom92.1%71.1%Claude Opus 4.6
APEX-Agents46.3%Not measuredOnly Claude Opus 4.6 measured
METR time horizons78.9%Not measuredOnly Claude Opus 4.6 measured
Remote Labor Index4.2%Not measuredOnly Claude Opus 4.6 measured
DeepResearch Bench55.3%Not measuredOnly Claude Opus 4.6 measured
Vending-Bench 2$8,018-$31Claude Opus 4.6
Berkeley Function Calling Leaderboard (BFCL)Not measured55.5%Only GPT-5 Mini measured
MCP Atlas76.8%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index141
Reasoning benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
GPQA Diamond89.7%80.3%Claude Opus 4.6
MMMU Pro (Vals AI)83.9%78.9%Claude Opus 4.6
GPQA Diamond (Artificial Analysis run)89.6%82.8%Claude Opus 4.6
Humanity's Last Exam (Artificial Analysis run)39.9%21.5%Claude Opus 4.6
GPQA Diamond (Epoch AI run)90.5%75.0%Claude Opus 4.6
ARC-AGI94.0%54.3%Claude Opus 4.6
ARC-AGI-269.2%4.4%Claude Opus 4.6
SimpleBench67.6%Not measuredOnly Claude Opus 4.6 measured
Chess puzzles21.0%24.0%GPT-5 Mini
Mystery game puzzles25.0%10.0%Claude Opus 4.6
EBR-bench12.7%Not measuredOnly Claude Opus 4.6 measured
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts15251380Claude Opus 4.6
LMArena Text: expert15441379Claude Opus 4.6
LMArena Text: hard prompts in English15301383Claude Opus 4.6
LMArena Vision: diagrams13401202Claude Opus 4.6
LMArena Vision: homework13371210Claude Opus 4.6
Kagi LLM Benchmark83.6%70.3%Claude Opus 4.6
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index80
Math benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
AIME95.6%91.5%Claude Opus 4.6
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)Not measured92.6%Only GPT-5 Mini measured
AA Math IndexNot measured90.7Only GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)Not measured90.7%Only GPT-5 Mini measured
OTIS Mock AIME94.4%86.7%Claude Opus 4.6
FrontierMath, tiers 1 to 366.0%46.7%Claude Opus 4.6
FrontierMath, tier 426.8%12.2%Claude Opus 4.6
ProofBench50.0%9.0%Claude Opus 4.6
MATH level 5Not measured97.8%Only GPT-5 Mini measured
LMArena Text: math15181378Claude Opus 4.6
LMArena Text: mathematical work15251380Claude Opus 4.6
MathArena23.6%14.8%Claude Opus 4.6
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index122
Knowledge benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
MMLU Pro89.1%82.2%Claude Opus 4.6
LegalBench (Vals AI)85.3%81.8%Claude Opus 4.6
CaseLaw (Vals AI)62.1%68.5%GPT-5 Mini
CorpFin (Vals AI)67.0%60.2%Claude Opus 4.6
TaxEval (Vals AI)76.0%75.2%Claude Opus 4.6
MortgageTax (Vals AI)68.5%66.9%Claude Opus 4.6
MedQA (Vals AI)95.4%96.1%GPT-5 Mini
MedCode (Vals AI)49.1%43.0%Claude Opus 4.6
MMLU Pro (Artificial Analysis run)Not measured83.7%Only GPT-5 Mini measured
SimpleQA Verified47.0%21.6%Claude Opus 4.6
LMArena Text: science15191371Claude Opus 4.6
LMArena Text: medicine and healthcare15041380Claude Opus 4.6
LMArena Text: legal and government15121375Claude Opus 4.6
LMArena Text: business and finance14971358Claude Opus 4.6
FACTS Benchmark Suite41.5%38.6%Claude Opus 4.6
PRBench Finance53.3%Not measuredOnly Claude Opus 4.6 measured
PRBench Legal52.3%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
Design Arena: websites12911125Claude Opus 4.6
Design Arena: UI components12821103Claude Opus 4.6
Design Arena: game dev12771129Claude Opus 4.6
Design Arena: data viz12801131Claude Opus 4.6
Design Arena: 3D12731036Claude Opus 4.6
Design Arena: all code categories12881114Claude Opus 4.6
Design Arena: SVG12271090Claude Opus 4.6
Design Arena: ASCII art12551125Claude Opus 4.6
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index292
General benchmarks for Claude Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
SAGE (Vals AI)51.6%43.0%Claude Opus 4.6
MedScribe (Vals AI)86.7%80.6%Claude Opus 4.6
IFBench53.1%75.4%GPT-5 Mini
Long context reasoning (AA-LCR)78.0%72.3%Claude Opus 4.6
DTBench91.2%80.5%Claude Opus 4.6
LMCA55.8%34.2%Claude Opus 4.6
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.6 measured
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011373Claude Opus 4.6
LMArena Text: instruction following15211357Claude Opus 4.6
LMArena Text: creative writing15051325Claude Opus 4.6
LMArena Vision13161202Claude Opus 4.6
LMArena Text: English15111379Claude Opus 4.6
LMArena Text: non-English14881363Claude Opus 4.6
LMArena Text: Chinese15511386Claude Opus 4.6
LMArena Text: German15001366Claude Opus 4.6
LMArena Text: Japanese14881341Claude Opus 4.6
LMArena Text: Korean14641308Claude Opus 4.6
LMArena Text: French15121386Claude Opus 4.6
LMArena Text: Spanish15101354Claude Opus 4.6
LMArena Text: Russian14971362Claude Opus 4.6
LMArena Text: Polish14991378Claude Opus 4.6
LMArena Text: multi-turn15111363Claude Opus 4.6
LMArena Text: longer queries15181355Claude Opus 4.6
LMArena Text: writing and language15021344Claude Opus 4.6
LMArena Text: entertainment and media14921340Claude Opus 4.6
LMArena Vision: English13241216Claude Opus 4.6
LMArena Vision: Chinese13701214Claude Opus 4.6
LMArena Vision: reading text13261199Claude Opus 4.6
LMArena Vision: humor13141205Claude Opus 4.6
LMArena Vision: captioningNot measured1217Only GPT-5 Mini measured
LMArena Vision: recognizing things12741226Claude Opus 4.6
LMArena Vision: creative writing13311181Claude Opus 4.6
LMArena Document1507Not measuredOnly Claude Opus 4.6 measured
MultiChallenge56.0%59.0%GPT-5 Mini
EQ-Bench 41223Not measuredOnly Claude Opus 4.6 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 Opus 4.6 and GPT-5 Mini
BenchmarkClaude Opus 4.6GPT-5 MiniLeader
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 4.6$0.018Fits in one request
GPT-5 Mini$0.0013Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
GPT-5 Mini$0.070Fits in one request

GPT-5 Mini 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 4.6 and GPT-5 Mini
SpecificationAnthropic Claude Opus 4.6OpenAI GPT-5 Mini
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026August 7, 2025
Context window1M400K
Input $/Mtok$5.00$0.25
Output $/Mtok$25.00$2.00
Coding index57.234.2
Independent measurements behind it42
Cost per solved task$1.56$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than GPT-5 Mini for coding?

Pick Claude Opus 4.6 for coding: it scores 57.2 on the Vibe Coding Index against 34.2 for GPT-5 Mini. Pick GPT-5 Mini for output tokens 12.5x cheaper ($2.00 vs $25.00 per million) and a lower cost per solved task ($0.08 against $1.56).

Which is cheaper, Claude Opus 4.6 or GPT-5 Mini?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and GPT-5 Mini $0.08.

Which has the bigger context window, Claude Opus 4.6 or GPT-5 Mini?

Claude Opus 4.6, with 1M tokens against 400K.

How many benchmarks is the Claude Opus 4.6 vs GPT-5 Mini comparison based on?

90 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.6's coding index rests on 4 independent benchmarks and GPT-5 Mini'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-opus-4-6-vs-gpt-5-mini" title="Claude Opus 4.6 vs GPT-5 Mini, 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-4-6-vs-gpt-5-mini">LLMBenchmark.ai, Claude Opus 4.6 vs GPT-5 Mini</a></p>