DataLearner logo

GPT-5.3 CodexvsClaude Opus 4.6

GPT-5.3 Codex and Claude Opus 4.6 are tied across 4 shared benchmarks: GPT-5.3 Codex leads on 2, Claude Opus 4.6 leads on 2, with 0 ties and an average score difference of -31.74.

OpenAI
GPT-5.3 Codex

OpenAI · 2026-02-05 · Coding model

Anthropic
Claude Opus 4.6

Anthropic · 2026-02-05 · Reasoning model

GPT-5.3 Codex2 wins(50%)(50%)2 winsClaude Opus 4.6

Benchmark scores

Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.

Coding and Software Engineer

Even 2/2
BenchmarkGPT-5.3 CodexClaude Opus 4.6Diff
Text Arena (Coding)1,40728 / 35Normal (No Tools)1,5558 / 35Normal (No Tools)-148.70
WeirdML v279.308 / 52Normal (With Tools)65.9023 / 52Normal (With Tools)+13.40

AI Agent - Tool Usage

GPT-5.3 Codex 1/1
BenchmarkGPT-5.3 CodexClaude Opus 4.6Diff
Terminal Bench 2.077.303 / 4765.4011 / 47Extended (with tools)+11.90

General Knowledge

Claude Opus 4.6 1/1
BenchmarkGPT-5.3 CodexClaude Opus 4.6Diff
LiveBench72.7625 / 115Thinking High (No Tools)76.338 / 115Thinking High (No Tools)-3.57

Specs

FieldGPT-5.3 CodexClaude Opus 4.6
PublisherOpenAIAnthropic
Release date2026-02-052026-02-05
Model typeCoding modelReasoning model
ArchitectureDenseDense
ParametersNot availableNot available
Context length400K1000K
Max output125K64K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGPT-5.3 CodexClaude Opus 4.6
Text input$1.75 / 1M tokens$0.5 / 1M tokens
Text output$14 / 1M tokens$25 / 1M tokens
Cache read$0.175 / 1M tokens$0.5 / 1M tokens
Cache writeNot public$10 / 1M tokens

Summary

  • GPT-5.3 Codexleads in:AI Agent - Tool Usage (1/1)
  • Claude Opus 4.6leads in:General Knowledge (1/1)
  • Tied in:Coding and Software Engineer

On average across the 4 shared benchmarks, Claude Opus 4.6 scores 31.74 higher.

Largest single-benchmark gap: Text Arena (Coding) — GPT-5.3 Codex 1,407 vs Claude Opus 4.6 1,555 (-148.70).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.