LLM·Dex
Newsletter

Claude Sonnet 4.6 vs GPT-5

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Updated

Claude Sonnet 4.6 specs · GPT-5 specs
Verdict by category
  • PriceGPT-5

    GPT-5 publishes pricing ($10.00 / 1M output tokens) while Claude Sonnet 4.6 does not.

  • Context windowGPT-5

    GPT-5 accepts 400K tokens vs 200K, 2.0× the room for long documents and codebases.

  • BenchmarksTie

    No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.

  • ModalitiesGPT-5

    GPT-5 supports 3 modalities (text, vision, audio) vs 2 for Claude Sonnet 4.6.

  • OpennessTie

    Both are closed-weight, API-only.

On balance GPT-5 edges ahead, winning 3 of 5 categories against Claude Sonnet 4.6's 0. GPT-5 publishes pricing ($10.00 / 1M output tokens) while Claude Sonnet 4.6 does not. GPT-5 accepts 400K tokens vs 200K, 2.0× the room for long documents and codebases.

No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. They differ in modality coverage, Claude Sonnet 4.6 handles text, vision while GPT-5 handles text, vision, audio, which can be the deciding factor before you even look at benchmarks. Both are closed-weight, API-only.

Claude Sonnet 4.6 is the newer of the two, released 6 months after GPT-5, which usually means a more recent knowledge cutoff and updated safety post-training. Claude Sonnet 4.6 is usually picked for coding llm and code review workloads, while GPT-5 sees more deployments in coding llm and agents. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecClaude Sonnet 4.6GPT-5
ProviderAnthropicOpenAI
ReleasedJan 2026Aug 2025
Modalitiestext, visiontext, vision, audio
Context window200K tokens400K tokens
Max output,128K tokens
Input · 1MPricing not published$1.25 / 1M tokens
Output · 1MPricing not published$10.00 / 1M tokens
Knowledge cutoff,2024-09
Open weightsNoNo
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day, vs $18.75
  • Heavy usage, 1M in / 500k out per day, vs $188
  • RAG workload, 5M in / 200k out per day, vs $248

Light usage, 100k in / 50k out per day: pricing not directly comparable (one or both models are missing public per-token rates). Heavy usage, 1M in / 500k out per day: pricing not directly comparable (one or both models are missing public per-token rates). RAG workload, 5M in / 200k out per day: pricing not directly comparable (one or both models are missing public per-token rates).

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Claude Sonnet 4.6Pricing unavailable
  • GPT-5$0.625

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Claude Sonnet 4.6GPT-5
  • MMLU,91.4
  • HumanEval,96.2
  • GPQA,89.4
  • SWE-bench Verified,74.9
Pick Claude Sonnet 4.6 if

Claude Sonnet 4.6 fits when…

  • Excellent quality-cost ratio
  • Strong for code review and writing
  • Reliable tool-use
Pick GPT-5 if

GPT-5 fits when…

  • Unified model, reasoning routed automatically per query
  • Excellent tool-use and JSON-mode discipline
  • Strong agent performance on SWE-bench Verified
  • Long-context tasks, handles 400K tokens vs 200K for Claude Sonnet 4.6.
  • Multimodal needs covering audio.
Don't want either?

Consider Claude Opus 4.7

Anthropic's mid-2026 flagship, ahead on SWE-bench, agent reliability, and writing quality.

See Claude Opus 4.7 specsClaude Sonnet 4.6 vs Claude Opus 4.7GPT-5 vs Claude Opus 4.7

Frequently asked

  • Is Claude Sonnet 4.6 or GPT-5 cheaper?
    Per-token pricing isn't published for at least one of these models, check each model's spec page for current rates.
  • Which has the larger context window?
    GPT-5 accepts 400K tokens vs 200K for Claude Sonnet 4.6.
  • Is Claude Sonnet 4.6 or GPT-5 better for coding?
    Both Claude Sonnet 4.6 and GPT-5 are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Neither model ships open weights, both are accessible only via their respective providers' APIs.
  • When were Claude Sonnet 4.6 and GPT-5 released?
    Claude Sonnet 4.6 was released by Anthropic on 2026-01-20. GPT-5 was released by OpenAI on 2025-08-07.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.