Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs GPT-5.3-Codex

GPT-5.3-Codex leads Claude Opus 4.6 on coding, 60.0 to 57.2 on the Vibe Coding Index, and GPT-5.3-Codex costs 1.8x less per output token ($14.00 vs $25.00 per million). Updated October 21, 2026; 31 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace GPT-5.3-Codex
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
21
GPT-5.3-CodexOpenAI
Coding
60.0
Overall
No data
Output $/M
$14.00
10
vs boards won of 31 shared

Claude Opus 4.6 or GPT-5.3-Codex: which to pick

Pick GPT-5.3-Codex for coding: it scores 60.0 on the Vibe Coding Index against 57.2 for Claude Opus 4.6, though on 3 benchmarks against 4.

Pick Claude Opus 4.6 for a larger context window (1M against 400K tokens) and work measured by LMArena WebDev or SWE-bench Verified (Vals AI), where it leads.

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BGPT-5.3-CodexOpenAI60.0/1003 independent benchmarks$0.59 per solved task
Shared results
31
Claude Opus 4.6 only
79
GPT-5.3-Codex only
3
Like-for-like categories
6 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-5.3-Codex 60.0 from 3 benchmarks.
Widest category
Web design, 17.5 points apart on average over 8 shared benchmarks.
Widest single gap
Design Arena: 3D: Claude Opus 4.6 1274 against GPT-5.3-Codex 1008, 33.3 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against GPT-5.3-Codex $14.00 per million output tokens, 1.8x apart.
Context window
Claude Opus 4.6 takes 1M tokens, GPT-5.3-Codex 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-5.3-CodexTies
Coding64
Intelligence02
Agentic work70
Reasoning02
Web design80
General02
All shared boards2110
CodingLike-for-likeSix of these boards feed the Vibe Coding Index64
Coding benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
SWE-bench Verified75.6%Not measuredOnly Claude Opus 4.6 measured
SWE-bench Multilingual72.0%Not measuredOnly Claude Opus 4.6 measured
LMArena WebDev15471407Claude Opus 4.6
LiveCodeBench (Vals AI)84.7%87.3%GPT-5.3-Codex
SWE-bench Verified (Vals AI)78.2%78.0%Claude Opus 4.6
Vibe Code Bench (Vals AI)57.6%61.8%GPT-5.3-Codex
IOI (Vals AI)Not measured53.8%Only GPT-5.3-Codex measured
Terminal-Bench Hard (Artificial Analysis run)48.5%53.0%GPT-5.3-Codex
Terminal-Bench79.8%78.4%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%79.3%GPT-5.3-Codex
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
ALE-BenchNot measured1655.2Only GPT-5.3-Codex measured
LMArena Text: coding1534Not measuredOnly Claude Opus 4.6 measured
LMArena Text: software and IT1527Not measuredOnly Claude Opus 4.6 measured
LMArena WebDev: React15391395Claude Opus 4.6
LMArena WebDev: HTML15591422Claude Opus 4.6
LMArena WebDev: from an image15431443Claude Opus 4.6
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
AA Intelligence Index31.932.5GPT-5.3-Codex
Epoch Capabilities Index155.7157.1GPT-5.3-Codex
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
Agentic work benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
Design Arena: agents building web apps12061032Claude Opus 4.6
Design Arena: agents building full-stack apps1220983Claude Opus 4.6
Design Arena: agents building mobile apps12071054Claude Opus 4.6
Design Arena: agents building Android apps11961084Claude Opus 4.6
Design Arena: agents building Godot gamesNot measured1124Only GPT-5.3-Codex measured
Design Arena: agents building games1212Not measuredOnly Claude Opus 4.6 measured
τ²-Bench Telecom92.1%86.0%Claude Opus 4.6
APEX-Agents46.3%Not measuredOnly Claude Opus 4.6 measured
METR time horizons78.9%74.5%Claude Opus 4.6
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$5,940Claude Opus 4.6
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
Reasoning benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
GPQA Diamond89.7%Not measuredOnly Claude Opus 4.6 measured
MMMU Pro (Vals AI)83.9%Not measuredOnly Claude Opus 4.6 measured
GPQA Diamond (Artificial Analysis run)89.6%91.5%GPT-5.3-Codex
Humanity's Last Exam (Artificial Analysis run)39.9%42.5%GPT-5.3-Codex
GPQA Diamond (Epoch AI run)90.5%Not measuredOnly Claude Opus 4.6 measured
ARC-AGI94.0%Not measuredOnly Claude Opus 4.6 measured
ARC-AGI-269.2%Not measuredOnly Claude Opus 4.6 measured
SimpleBench67.6%Not measuredOnly Claude Opus 4.6 measured
Chess puzzles21.0%Not measuredOnly Claude Opus 4.6 measured
Mystery game puzzles25.0%Not measuredOnly Claude Opus 4.6 measured
EBR-bench12.7%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: hard prompts1525Not measuredOnly Claude Opus 4.6 measured
LMArena Text: expert1544Not measuredOnly Claude Opus 4.6 measured
LMArena Text: hard prompts in English1530Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: diagrams1340Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: homework1337Not measuredOnly Claude Opus 4.6 measured
Kagi LLM Benchmark83.6%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 5 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
AIME95.6%Not measuredOnly Claude Opus 4.6 measured
OTIS Mock AIME94.4%Not measuredOnly Claude Opus 4.6 measured
FrontierMath, tiers 1 to 366.0%Not measuredOnly Claude Opus 4.6 measured
FrontierMath, tier 426.8%Not measuredOnly Claude Opus 4.6 measured
ProofBench50.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: math1518Not measuredOnly Claude Opus 4.6 measured
LMArena Text: mathematical work1525Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 6 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
Knowledge benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
MMLU Pro89.1%Not measuredOnly Claude Opus 4.6 measured
LegalBench (Vals AI)85.3%Not measuredOnly Claude Opus 4.6 measured
CaseLaw (Vals AI)62.1%Not measuredOnly Claude Opus 4.6 measured
CorpFin (Vals AI)67.0%Not measuredOnly Claude Opus 4.6 measured
TaxEval (Vals AI)76.0%Not measuredOnly Claude Opus 4.6 measured
MortgageTax (Vals AI)68.5%Not measuredOnly Claude Opus 4.6 measured
MedQA (Vals AI)95.4%Not measuredOnly Claude Opus 4.6 measured
MedCode (Vals AI)49.1%Not measuredOnly Claude Opus 4.6 measured
SimpleQA Verified47.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: science1519Not measuredOnly Claude Opus 4.6 measured
LMArena Text: medicine and healthcare1504Not measuredOnly Claude Opus 4.6 measured
LMArena Text: legal and government1512Not measuredOnly Claude Opus 4.6 measured
LMArena Text: business and finance1497Not measuredOnly Claude Opus 4.6 measured
FACTS Benchmark Suite41.5%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 4 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-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
Design Arena: websites12911163Claude Opus 4.6
Design Arena: UI components12841137Claude Opus 4.6
Design Arena: game dev12781161Claude Opus 4.6
Design Arena: data viz12791164Claude Opus 4.6
Design Arena: 3D12741008Claude Opus 4.6
Design Arena: all code categories12891145Claude Opus 4.6
Design Arena: SVG12281129Claude Opus 4.6
Design Arena: ASCII art12551152Claude 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 index02
General benchmarks for Claude Opus 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
SAGE (Vals AI)51.6%Not measuredOnly Claude Opus 4.6 measured
MedScribe (Vals AI)86.7%Not measuredOnly Claude Opus 4.6 measured
IFBench53.1%75.4%GPT-5.3-Codex
Long context reasoning (AA-LCR)78.0%83.3%GPT-5.3-Codex
DTBench91.2%Not measuredOnly Claude Opus 4.6 measured
LMCA55.8%Not measuredOnly Claude Opus 4.6 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 Text1501Not measuredOnly Claude Opus 4.6 measured
LMArena Text: instruction following1521Not measuredOnly Claude Opus 4.6 measured
LMArena Text: creative writing1505Not measuredOnly Claude Opus 4.6 measured
LMArena Vision1316Not measuredOnly Claude Opus 4.6 measured
LMArena Text: English1511Not measuredOnly Claude Opus 4.6 measured
LMArena Text: non-English1488Not measuredOnly Claude Opus 4.6 measured
LMArena Text: Chinese1551Not measuredOnly Claude Opus 4.6 measured
LMArena Text: German1500Not measuredOnly Claude Opus 4.6 measured
LMArena Text: Japanese1488Not measuredOnly Claude Opus 4.6 measured
LMArena Text: Korean1464Not measuredOnly Claude Opus 4.6 measured
LMArena Text: French1512Not measuredOnly Claude Opus 4.6 measured
LMArena Text: Spanish1510Not measuredOnly Claude Opus 4.6 measured
LMArena Text: Russian1497Not measuredOnly Claude Opus 4.6 measured
LMArena Text: Polish1499Not measuredOnly Claude Opus 4.6 measured
LMArena Text: multi-turn1511Not measuredOnly Claude Opus 4.6 measured
LMArena Text: longer queries1518Not measuredOnly Claude Opus 4.6 measured
LMArena Text: writing and language1502Not measuredOnly Claude Opus 4.6 measured
LMArena Text: entertainment and media1492Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: English1324Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: Chinese1370Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: reading text1326Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: humor1314Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: recognizing things1274Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: creative writing1331Not measuredOnly Claude Opus 4.6 measured
LMArena Document1507Not measuredOnly Claude Opus 4.6 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 4.6 and GPT-5.3-Codex
BenchmarkClaude Opus 4.6GPT-5.3-CodexLeader
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-5.3-Codex$0.0088Fits in one request

GPT-5.3-Codex costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
GPT-5.3-Codex$0.130Fits in one request

GPT-5.3-Codex costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
GPT-5.3-Codex$0.490Fits in one request

GPT-5.3-Codex 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-5.3-Codex
SpecificationAnthropic Claude Opus 4.6OpenAI GPT-5.3-Codex
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026February 24, 2026
Context window1M400K
Input $/Mtok$5.00$1.75
Output $/Mtok$25.00$14.00
Coding index57.260.0
Independent measurements behind it43
Cost per solved task$1.56$0.59
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than GPT-5.3-Codex for coding?

Pick GPT-5.3-Codex for coding: it scores 60.0 on the Vibe Coding Index against 57.2 for Claude Opus 4.6, though on 3 benchmarks against 4. Pick Claude Opus 4.6 for a larger context window (1M against 400K tokens) and work measured by LMArena WebDev or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, Claude Opus 4.6 or GPT-5.3-Codex?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.3-Codex costs $1.75 and $14.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and GPT-5.3-Codex $0.59.

Which has the bigger context window, Claude Opus 4.6 or GPT-5.3-Codex?

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

How many benchmarks is the Claude Opus 4.6 vs GPT-5.3-Codex comparison based on?

31 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.6's coding index rests on 4 independent benchmarks and GPT-5.3-Codex's on 3. 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-5-3-codex" title="Claude Opus 4.6 vs GPT-5.3-Codex, 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-5-3-codex">LLMBenchmark.ai, Claude Opus 4.6 vs GPT-5.3-Codex</a></p>