LLM Rank.top

Leaderboard · Model · Updated

Claude Sonnet 4

Balanced cost/quality Claude — default workhorse for most production traffic.

Composite 80.7 Rank #7 of 30 Anthropic general-purpose Closed / proprietary Released 2025-05
Try Claude Sonnet 4 → Compare with Grok 3 → Or route via OpenRouter →

At a glance

ProviderAnthropic
Released2025-05
Tiergeneral-purpose
LicenseClosed / proprietary
Modalitiestext, image
Context window200k tokens
Max output64k tokens
API price · input$3.00 / 1M tokens
API price · output$15.00 / 1M tokens

Benchmark performance

How Claude Sonnet 4 stacks up against the current leader (GPT-5) and the median model in the leaderboard:

BenchmarkClaude Sonnet 4GPT-5Median
Chatbot Arena Elo 1370 1410 1320
MMLU-Pro 84.0 86.8 78.0
GPQA Diamond 75.4 87.3 65.0
MATH 93.0 96.7 78.3
HumanEval 93.7 95.1 92.0
SWE-Bench Verified 72.7 74.9 49.0

Numbers compiled from provider technical reports and Chatbot Arena. See methodology for the composite-score formula.

Don't lock in to one provider.

OpenRouter routes your requests across Claude Sonnet 4, GPT-5, Claude, Gemini, and 100+ other models behind a single API key — pay-as-you-go, no monthly minimum. Try OpenRouter → (affiliate · supports this site)

What does Claude Sonnet 4 cost in practice?

API pricing is $3.00 per 1M input tokens and $15.00 per 1M output tokens. Assuming a 50/50 input/output split, here is what that looks like at three workload sizes:

VolumePer dayPer monthPer year
1M tokens/day$9.00$270.00$3,285
10M tokens/day$90.00$2,700$32,850
100M tokens/day$900.00$27,000$328,500

Strengths & weaknesses

Where it shines

  • HumanEval: 93.7 (rank #3 of 30, top tier)
  • SWE-Bench: 72.7 (rank #3 of 18, top tier)
  • MMLU-Pro: 84.0 (rank #6 of 29, above average)

Where it lags

No clear weaknesses across published benchmarks.

Best alternatives

The closest models to Claude Sonnet 4 by tier and benchmark score:

ModelScore$ in / outContextAction
Grok 3
xAI
81.7 $3.00 / $15.00 1M Try → · vs Claude
Claude 3.7 Sonnet
Anthropic
76.0 $3.00 / $15.00 200k Try → · vs Claude
GPT-4.1
OpenAI
74.5 $2.00 / $8.00 1M Try → · vs Claude
Claude 3.5 Sonnet
Anthropic
69.1 $3.00 / $15.00 200k Try → · vs Claude
Gemini 1.5 Pro
Google
67.9 $1.25 / $5.00 2M Try → · vs Claude

Frequently asked questions

Is Claude Sonnet 4 a good model?

Claude Sonnet 4 scores 80.7 on the llmrank.top composite (rank #7 of 30). It is competitive with the leaders (GPT-5 tops the board at 86.0). Whether it's the right fit depends on your workload — see the use-case discussion on this page.

How much does Claude Sonnet 4 cost?

Claude Sonnet 4 is priced at $3.00 per 1M input tokens and $15.00 per 1M output tokens (USD). For a 10M-token-per-day workload split 50/50, that works out to roughly $90.00/day or $32,850/year.

What is Claude Sonnet 4's context window?

200k tokens. That covers most multi-document workloads.

Is Claude Sonnet 4 open source?

No — it is a closed (proprietary) model accessed only via the provider API.

What is Claude Sonnet 4's SWE-Bench score?

Claude Sonnet 4 scores 72.7% on SWE-Bench Verified — the benchmark that measures real-world GitHub issue resolution. Its Chatbot Arena Elo is 1370.

What are the best alternatives to Claude Sonnet 4?

Closest alternatives by tier and score: Grok 3, Claude 3.7 Sonnet, GPT-4.1. See the alternatives section on this page for side-by-side numbers.


Related: Grok 3 · Claude 3.7 Sonnet · GPT-4.1 · Full leaderboard

Spotted out-of-date numbers? Open an issue — corrections usually ship within 24h.

Try Claude Sonnet 4 now

Direct link to the official playground — or use OpenRouter to A/B test it against any other model on a single API key.

Open Anthropic playground → Try via OpenRouter →