Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs GPT-5 Mini

Claude Sonnet 4.5 leads GPT-5 Mini on coding, 39.5 to 34.2 on the Vibe Coding Index, and GPT-5 Mini costs 7.5x less per output token ($2.00 vs $15.00 per million). Updated October 22, 2026; 77 benchmarks have a result for both.

Replace Claude Sonnet 4.5 Replace GPT-5 Mini
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
62
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
15
vs boards won of 77 shared

Claude Sonnet 4.5 or GPT-5 Mini: which to pick

Pick Claude Sonnet 4.5 for coding: it scores 39.5 on the Vibe Coding Index against 34.2 for GPT-5 Mini.

Pick GPT-5 Mini for output tokens 7.5x cheaper ($2.00 vs $15.00 per million) and a lower cost per solved task ($0.08 against $1.16).

Model AClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved taskModel BGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved task
Shared results
77
Claude Sonnet 4.5 only
18
GPT-5 Mini only
24
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 Sonnet 4.5 39.5 from 3 benchmarks, GPT-5 Mini 34.2 from 2 benchmarks.
Widest category
Agentic work, 20.9 points apart on average over 2 shared benchmarks.
Widest single gap
SWE-bench Multilingual: Claude Sonnet 4.5 67.0% against GPT-5 Mini 39.7%, 27.3 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.5 $15.00 against GPT-5 Mini $2.00 per million output tokens, 7.5x apart.
Context window
Claude Sonnet 4.5 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 Sonnet 4.5BarsGPT-5 MiniTies
Coding72
Intelligence20
Agentic work20
Reasoning93
Math45
Knowledge104
Web design80
General201
All shared boards6215
CodingLike-for-likeSix of these boards feed the Vibe Coding Index72
Coding benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
SWE-bench Verified74.8%59.8%Claude Sonnet 4.5
SWE-bench Multilingual67.0%39.7%Claude Sonnet 4.5
LMArena WebDev1394Not measuredOnly Claude Sonnet 4.5 measured
AA Coding Index52.1Not measuredOnly Claude Sonnet 4.5 measured
LiveCodeBench (Vals AI)73.0%86.6%GPT-5 Mini
SWE-bench Verified (Vals AI)70.0%60.8%Claude Sonnet 4.5
Vibe Code Bench (Vals AI)22.6%14.2%Claude Sonnet 4.5
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)Not measured33.3%Only GPT-5 Mini measured
Terminal-Bench46.5%34.8%Claude Sonnet 4.5
GSO-Bench14.7%Not measuredOnly Claude Sonnet 4.5 measured
WeirdML47.7%52.7%GPT-5 Mini
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: coding14881406Claude Sonnet 4.5
LMArena Text: software and IT14731394Claude Sonnet 4.5
LMArena WebDev: React1386Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev: HTML1399Not measuredOnly Claude Sonnet 4.5 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 Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
AA Intelligence Index20.720.6Claude Sonnet 4.5
Epoch Capabilities Index146.7145.3Claude Sonnet 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
AA Agentic Index15.8Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building web apps1060Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building full-stack apps1050Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building mobile apps1137Not measuredOnly Claude Sonnet 4.5 measured
τ²-Bench TelecomNot measured71.1%Only GPT-5 Mini measured
METR time horizons67.4%Not measuredOnly Claude Sonnet 4.5 measured
Remote Labor Index2.1%Not measuredOnly Claude Sonnet 4.5 measured
GDPval42.5%Not measuredOnly Claude Sonnet 4.5 measured
DeepResearch Bench52.6%Not measuredOnly Claude Sonnet 4.5 measured
OSWorld62.9%Not measuredOnly Claude Sonnet 4.5 measured
Vending-Bench 2$3,839-$31Claude Sonnet 4.5
Berkeley Function Calling Leaderboard (BFCL)73.2%55.5%Claude Sonnet 4.5
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index93
Reasoning benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
GPQA Diamond81.6%80.3%Claude Sonnet 4.5
MMMU Pro (Vals AI)79.3%78.9%Claude Sonnet 4.5
GPQA Diamond (Artificial Analysis run)Not measured82.8%Only GPT-5 Mini measured
Humanity's Last Exam (Artificial Analysis run)Not measured21.5%Only GPT-5 Mini measured
GPQA Diamond (Epoch AI run)82.3%75.0%Claude Sonnet 4.5
ARC-AGI63.7%54.3%Claude Sonnet 4.5
ARC-AGI-213.6%4.4%Claude Sonnet 4.5
SimpleBench54.3%Not measuredOnly Claude Sonnet 4.5 measured
Chess puzzles10.0%24.0%GPT-5 Mini
Mystery game puzzles17.0%10.0%Claude Sonnet 4.5
EBR-bench2.4%Not measuredOnly Claude Sonnet 4.5 measured
VPCT39.8%40.2%GPT-5 Mini
LMArena Text: hard prompts14621380Claude Sonnet 4.5
LMArena Text: expert14831379Claude Sonnet 4.5
LMArena Text: hard prompts in English14711383Claude Sonnet 4.5
LMArena Vision: diagramsNot measured1202Only GPT-5 Mini measured
LMArena Vision: homeworkNot measured1210Only GPT-5 Mini measured
Kagi LLM Benchmark57.9%70.3%GPT-5 Mini
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index45
Math benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
AIME88.2%91.5%GPT-5 Mini
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)94.3%92.6%Claude Sonnet 4.5
AA Math IndexNot measured90.7Only GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)Not measured90.7%Only GPT-5 Mini measured
OTIS Mock AIME77.8%86.7%GPT-5 Mini
FrontierMath, tiers 1 to 323.9%46.7%GPT-5 Mini
FrontierMath, tier 42.4%12.2%GPT-5 Mini
ProofBench19.0%9.0%Claude Sonnet 4.5
MATH level 597.7%97.8%GPT-5 Mini
LMArena Text: math14491378Claude Sonnet 4.5
LMArena Text: mathematical work14621380Claude Sonnet 4.5
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index104
Knowledge benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
MMLU Pro87.4%82.2%Claude Sonnet 4.5
LegalBench (Vals AI)84.1%81.8%Claude Sonnet 4.5
CaseLaw (Vals AI)62.2%68.5%GPT-5 Mini
CorpFin (Vals AI)62.0%60.2%Claude Sonnet 4.5
TaxEval (Vals AI)73.3%75.2%GPT-5 Mini
MortgageTax (Vals AI)64.0%66.9%GPT-5 Mini
MedQA (Vals AI)94.7%96.1%GPT-5 Mini
MedCode (Vals AI)44.1%43.0%Claude Sonnet 4.5
MMLU Pro (Artificial Analysis run)Not measured83.7%Only GPT-5 Mini measured
SimpleQA Verified30.7%21.6%Claude Sonnet 4.5
LMArena Text: science14481371Claude Sonnet 4.5
LMArena Text: medicine and healthcare14441380Claude Sonnet 4.5
LMArena Text: legal and government14511375Claude Sonnet 4.5
LMArena Text: business and finance14401358Claude Sonnet 4.5
FACTS Benchmark Suite40.6%38.6%Claude Sonnet 4.5
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 Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
Design Arena: websites11891125Claude Sonnet 4.5
Design Arena: UI components11701103Claude Sonnet 4.5
Design Arena: game dev11661129Claude Sonnet 4.5
Design Arena: data viz11671131Claude Sonnet 4.5
Design Arena: 3D11571036Claude Sonnet 4.5
Design Arena: all code categories11821114Claude Sonnet 4.5
Design Arena: SVG11151091Claude Sonnet 4.5
Design Arena: ASCII art12051125Claude Sonnet 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-5 MiniLeader
SAGE (Vals AI)36.1%43.0%GPT-5 Mini
MedScribe (Vals AI)84.5%80.6%Claude Sonnet 4.5
IFBenchNot measured75.4%Only GPT-5 Mini measured
Long context reasoning (AA-LCR)Not measured72.3%Only GPT-5 Mini measured
DTBench83.2%80.5%Claude Sonnet 4.5
LMCA38.8%34.2%Claude Sonnet 4.5
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
LMArena Text14381373Claude Sonnet 4.5
LMArena Text: instruction following14591357Claude Sonnet 4.5
LMArena Text: creative writing14421325Claude Sonnet 4.5
LMArena VisionNot measured1202Only GPT-5 Mini measured
LMArena Text: English14501379Claude Sonnet 4.5
LMArena Text: non-English14251363Claude Sonnet 4.5
LMArena Text: Chinese14601386Claude Sonnet 4.5
LMArena Text: German14271366Claude Sonnet 4.5
LMArena Text: Japanese13901341Claude Sonnet 4.5
LMArena Text: Korean14021308Claude Sonnet 4.5
LMArena Text: French14591386Claude Sonnet 4.5
LMArena Text: Spanish14581354Claude Sonnet 4.5
LMArena Text: Russian14371362Claude Sonnet 4.5
LMArena Text: Polish14231378Claude Sonnet 4.5
LMArena Text: multi-turn14651363Claude Sonnet 4.5
LMArena Text: longer queries14751355Claude Sonnet 4.5
LMArena Text: writing and language14421344Claude Sonnet 4.5
LMArena Text: entertainment and media14281340Claude Sonnet 4.5
LMArena Vision: EnglishNot measured1216Only GPT-5 Mini measured
LMArena Vision: ChineseNot measured1214Only GPT-5 Mini measured
LMArena Vision: reading textNot measured1199Only GPT-5 Mini measured
LMArena Vision: humorNot measured1205Only GPT-5 Mini measured
LMArena Vision: captioningNot measured1217Only GPT-5 Mini measured
LMArena Vision: recognizing thingsNot measured1226Only GPT-5 Mini measured
LMArena Vision: creative writingNot measured1181Only GPT-5 Mini measured
LMArena Document1450Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.5 and GPT-5 Mini
BenchmarkClaude Sonnet 4.5GPT-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 Sonnet 4.5$0.011Fits in one request
GPT-5 Mini$0.0013Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits 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 Sonnet 4.5 and GPT-5 Mini
SpecificationAnthropic Claude Sonnet 4.5OpenAI GPT-5 Mini
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2025August 7, 2025
Context window1M400K
Input $/Mtok$3.00$0.25
Output $/Mtok$15.00$2.00
Coding index39.534.2
Independent measurements behind it32
Cost per solved task$1.16$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than GPT-5 Mini for coding?

Pick Claude Sonnet 4.5 for coding: it scores 39.5 on the Vibe Coding Index against 34.2 for GPT-5 Mini. Pick GPT-5 Mini for output tokens 7.5x cheaper ($2.00 vs $15.00 per million) and a lower cost per solved task ($0.08 against $1.16).

Which is cheaper, Claude Sonnet 4.5 or GPT-5 Mini?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and GPT-5 Mini $0.08.

Which has the bigger context window, Claude Sonnet 4.5 or GPT-5 Mini?

Claude Sonnet 4.5, with 1M tokens against 400K.

How many benchmarks is the Claude Sonnet 4.5 vs GPT-5 Mini comparison based on?

77 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.5's coding index rests on 3 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-sonnet-4-5-vs-gpt-5-mini" title="Claude Sonnet 4.5 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-sonnet-4-5-vs-gpt-5-mini">LLMBenchmark.ai, Claude Sonnet 4.5 vs GPT-5 Mini</a></p>