Claude Sonnet 4 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 specs · GPT-5 specs- PriceGPT-5
GPT-5 is roughly 1.5× cheaper on output tokens ($10.00 vs $15.00 per 1M).
- Context windowGPT-5
GPT-5 accepts 400K tokens vs 200K, 2.0× the room for long documents and codebases.
- BenchmarksGPT-5
GPT-5 leads in 1 of 1 shared benchmarks; the biggest gap is on SWE-bench Verified (real-world software engineering), where it scores 74.9 vs 65.0.
- ModalitiesGPT-5
GPT-5 supports 3 modalities (text, vision, audio) vs 2 for Claude Sonnet 4.
- OpennessTie
Both are closed-weight, API-only.
On balance GPT-5 edges ahead, winning 4 of 5 categories against Claude Sonnet 4's 0. GPT-5 is roughly 1.5× cheaper on output tokens ($10.00 vs $15.00 per 1M). GPT-5 accepts 400K tokens vs 200K, 2.0× the room for long documents and codebases.
GPT-5 leads in 1 of 1 shared benchmarks; the biggest gap is on SWE-bench Verified (real-world software engineering), where it scores 74.9 vs 65.0. They differ in modality coverage, Claude Sonnet 4 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.
GPT-5 is the newer of the two, released 3 months after Claude Sonnet 4, which usually means a more recent knowledge cutoff and updated safety post-training. Claude Sonnet 4 is usually picked for coding llm and rag 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
| Spec | Claude Sonnet 4 | GPT-5 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Released | May 2025 | Aug 2025 |
| Modalities | text, vision | text, vision, audio |
| Context window | 200K tokens | 400K tokens |
| Max output | , | 128K tokens |
| Input · 1M | $3.00 / 1M tokens | $1.25 / 1M tokens |
| Output · 1M | $15.00 / 1M tokens | $10.00 / 1M tokens |
| Knowledge cutoff | 2025-03 | 2024-09 |
| Open weights | No | No |
| API available | Yes | Yes |
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$31.50 vs $18.75
- Heavy usage, 1M in / 500k out per day$315 vs $188
- RAG workload, 5M in / 200k out per day$540 vs $248
Light usage, 100k in / 50k out per day: $31.50 vs $18.75 per month, model B comes out ahead. Heavy usage, 1M in / 500k out per day: $315 vs $188 per month, model B comes out ahead. RAG workload, 5M in / 200k out per day: $540 vs $248 per month, model B comes out ahead.
Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.
- Claude Sonnet 4$1.05
- 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.
- MMLU,91.4
- HumanEval,96.2
- GPQA,89.4
- SWE-bench Verified65.074.9
Claude Sonnet 4 fits when…
- Solid all-rounder
- Mature deployment ecosystem
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
- Cost-sensitive workloads, 1.5× cheaper than Claude Sonnet 4 on output tokens.
- Long-context tasks, handles 400K tokens vs 200K for Claude Sonnet 4.
Consider Claude Opus 4.7
Anthropic's mid-2026 flagship, ahead on SWE-bench, agent reliability, and writing quality.
Frequently asked
Is Claude Sonnet 4 or GPT-5 cheaper?
GPT-5 is cheaper at $10.00 / 1M tokens per million output tokens, vs $15.00 / 1M tokens for Claude Sonnet 4.Which has the larger context window?
GPT-5 accepts 400K tokens vs 200K for Claude Sonnet 4.Is Claude Sonnet 4 or GPT-5 better for coding?
Both Claude Sonnet 4 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 and GPT-5 released?
Claude Sonnet 4 was released by Anthropic on 2025-05-22. GPT-5 was released by OpenAI on 2025-08-07.
The week's AI launches, in your inbox.
One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.