LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.1 vs o3

Updated October 21, 2026. 62 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.1 Replace o3
Claude Opus 4.1Anthropic
Coding
27.2
Overall
22.8
Output $/M
$75.00
34
o3OpenAI
Coding
70.7
Overall
20.2
Output $/M
$8.00
28
vs boards won of 62 shared

Decision reading

Pick o3 for coding: it scores 70.7 on the Vibe Coding Index against 27.2 for Claude Opus 4.1.

Pick Claude Opus 4.1 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AClaude Opus 4.1Anthropic27.2/1001 independent benchmarkNo cost per solved taskModel Bo3OpenAI70.7/1002 independent benchmarks$0.571 per solved task
Shared results
62
Claude Opus 4.1 only
9
o3 only
35
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 Opus 4.1 27.2 from 1 benchmark, o3 70.7 from 2 benchmarks.
Widest category
Web design, 15.3 points apart on average over 5 shared benchmarks.
Widest single gap
FrontierMath, tiers 1 to 3: Claude Opus 4.1 12.6% against o3 33.3%, 20.7 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.1 $75.00 against o3 $8.00 per million output tokens, 9.4x apart.
Context window
Both take 200K tokens.

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 4.1Barso3Ties
Coding22
Intelligence11
Agentic work30
Reasoning45
Math43
Knowledge28
Web design41
General148
All shared boards3428
CodingLike-for-likeFour of these boards feed the Vibe Coding Index22
Coding benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
Aider polyglotNot measured81.3%Only o3 measured
SWE-bench VerifiedNot measured58.4%Only o3 measured
SWE-bench MultimodalNot measured36.0%Only o3 measured
LMArena WebDev1390Not measuredOnly Claude Opus 4.1 measured
LiveCodeBench (Vals AI)66.5%83.9%o3
LiveCodeBench (Artificial Analysis run)Not measured80.8%Only o3 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured37.1%Only o3 measured
Terminal-Bench38.0%Not measuredOnly Claude Opus 4.1 measured
GSO-BenchNot measured8.8%Only o3 measured
WeirdML45.9%52.4%o3
Cybench42.0%Not measuredOnly Claude Opus 4.1 measured
ALE-BenchNot measured933.5Only o3 measured
LMArena Text: coding14791407Claude Opus 4.1
LMArena Text: software and IT14561415Claude Opus 4.1
LMArena WebDev: HTML1399Not measuredOnly Claude Opus 4.1 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
AA Intelligence Index22.820.2Claude Opus 4.1
Epoch Capabilities Index144.1146.7o3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
Agentic work benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
τ²-Bench TelecomNot measured80.7%Only o3 measured
METR time horizons66.8%65.4%Claude Opus 4.1
GDPval43.6%30.8%Claude Opus 4.1
DeepResearch Bench48.3%45.2%Claude Opus 4.1
OSWorldNot measured23.0%Only o3 measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index45
Reasoning benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
GPQA Diamond76.3%84.1%o3
MMMU Pro (Vals AI)77.5%80.4%o3
GPQA Diamond (Artificial Analysis run)Not measured82.7%Only o3 measured
Humanity's Last Exam (Artificial Analysis run)Not measured20.1%Only o3 measured
GPQA Diamond (Epoch AI run)77.3%81.8%o3
ARC-AGINot measured60.8%Only o3 measured
ARC-AGI-2Not measured6.5%Only o3 measured
SimpleBench60.0%53.1%Claude Opus 4.1
Chess puzzlesNot measured37.0%Only o3 measured
Mystery game puzzles21.0%29.0%o3
EBR-bench7.9%Not measuredOnly Claude Opus 4.1 measured
VPCT35.0%52.0%o3
LMArena Text: hard prompts14421402Claude Opus 4.1
LMArena Text: expert14381402Claude Opus 4.1
LMArena Text: hard prompts in English14511411Claude Opus 4.1
LMArena Vision: diagramsNot measured1220Only o3 measured
LMArena Vision: homeworkNot measured1234Only o3 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index43
Math benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
AIME78.2%85.3%o3
MATH 500 (Vals AI)95.4%94.6%Claude Opus 4.1
MGSM (Vals AI)94.4%91.8%Claude Opus 4.1
AA Math IndexNot measured88.3Only o3 measured
AIME 2025 (Artificial Analysis run)Not measured88.3%Only o3 measured
OTIS Mock AIME68.9%84.4%o3
FrontierMath, tiers 1 to 312.6%33.3%o3
FrontierMath, tier 42.4%Not measuredOnly Claude Opus 4.1 measured
MATH level 5Not measured97.8%Only o3 measured
LMArena Text: math14311426Claude Opus 4.1
LMArena Text: mathematical work14341423Claude Opus 4.1
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index28
Knowledge benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
MMLU Pro87.9%85.6%Claude Opus 4.1
LegalBench (Vals AI)83.5%83.8%o3
CorpFin (Vals AI)Not measured59.7%Only o3 measured
TaxEval (Vals AI)73.7%74.6%o3
MortgageTax (Vals AI)61.1%65.7%o3
MedQA (Vals AI)93.6%96.1%o3
MedCode (Vals AI)47.2%47.3%o3
MMLU Pro (Artificial Analysis run)Not measured85.3%Only o3 measured
SimpleQA VerifiedNot measured49.4%Only o3 measured
GeoBenchNot measured74.0%Only o3 measured
LMArena Text: science14221429o3
LMArena Text: medicine and healthcare14161448o3
LMArena Text: legal and government14211428o3
LMArena Text: business and finance14061393Claude Opus 4.1
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index41
Web design benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
Design Arena: websites11771036Claude Opus 4.1
Design Arena: UI components11641016Claude Opus 4.1
Design Arena: game dev11721034Claude Opus 4.1
Design Arena: data viz11661200o3
Design Arena: 3D1153Not measuredOnly Claude Opus 4.1 measured
Design Arena: all code categories11711021Claude Opus 4.1
Design Arena: SVG1152Not measuredOnly Claude Opus 4.1 measured
Design Arena: ASCII art1167Not measuredOnly Claude Opus 4.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index148
General benchmarks for Claude Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
SAGE (Vals AI)31.4%41.8%o3
MedScribe (Vals AI)73.9%76.7%o3
IFBenchNot measured71.4%Only o3 measured
Long context reasoning (AA-LCR)Not measured74.7%Only o3 measured
DTBench80.0%84.8%o3
LMCA37.1%39.7%o3
Fiction.LiveBenchNot measured88.9%Only o3 measured
Creative writing (Lech Mazur)84.7%83.9%Claude Opus 4.1
CL-benchNot measured17.8%Only o3 measured
LMArena Text14191410Claude Opus 4.1
LMArena Text: instruction following14351368Claude Opus 4.1
LMArena Text: creative writing14121359Claude Opus 4.1
LMArena VisionNot measured1214Only o3 measured
LMArena Text: English14331417Claude Opus 4.1
LMArena Text: non-English14051401Claude Opus 4.1
LMArena Text: Chinese14271437o3
LMArena Text: German14131420o3
LMArena Text: Japanese13771403o3
LMArena Text: Korean13811370Claude Opus 4.1
LMArena Text: French14331430Claude Opus 4.1
LMArena Text: Spanish14481395Claude Opus 4.1
LMArena Text: Russian14221406Claude Opus 4.1
LMArena Text: Polish14131438o3
LMArena Text: multi-turn14441405Claude Opus 4.1
LMArena Text: longer queries14551372Claude Opus 4.1
LMArena Text: writing and language14181372Claude Opus 4.1
LMArena Text: entertainment and media13981373Claude Opus 4.1
LMArena Vision: EnglishNot measured1221Only o3 measured
LMArena Vision: ChineseNot measured1237Only o3 measured
LMArena Vision: reading textNot measured1218Only o3 measured
LMArena Vision: humorNot measured1222Only o3 measured
LMArena Vision: captioningNot measured1210Only o3 measured
LMArena Vision: recognizing thingsNot measured1234Only o3 measured
LMArena Vision: creative writingNot measured1201Only o3 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 Opus 4.1 and o3
BenchmarkClaude Opus 4.1o3Leader
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 4.1$0.052Fits in one request
o3$0.0060Fits in one request

o3 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.1$0.975Fits in one request
o3$0.124Fits in one request

o3 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.1$3.75Exceeds the context window
o3$0.480Exceeds the context window

o3 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 4.1 and o3
SpecificationAnthropic Claude Opus 4.1OpenAI o3
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 5, 2025April 16, 2025
Context window200K200K
Input $/Mtok$15.00$2.00
Output $/Mtok$75.00$8.00
Coding index27.270.7
Independent measurements behind it12
Cost per solved taskNot computable$0.571
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.1 better than o3 for coding?

Pick o3 for coding: it scores 70.7 on the Vibe Coding Index against 27.2 for Claude Opus 4.1. Pick Claude Opus 4.1 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Opus 4.1 or o3?

Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; o3 costs $2.00 and $8.00. Cost per solved task is known for o3 only.

Which has the bigger context window, Claude Opus 4.1 or o3?

Neither: both take 200K tokens.

How many benchmarks is the Claude Opus 4.1 vs o3 comparison based on?

62 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.1's coding index rests on 1 independent benchmark and o3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next