Skip to content
Get my AI grade

Anthropic

Claude Sonnet 4 benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place Claude Sonnet 4, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Oct 5, 2026Full leaderboardSources and method

Read Oct 5, 2026

#72of 126

on the LLM leaderboard, with a consensus score of 46 across 2 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places Claude Sonnet 4

Artificial Analysis

#60of 115

Score 18.9. Best run: anthropic/claude-sonnet-4.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

Not measured by LiveBench.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

#69of 115

Score 1399. Best run: claude-sonnet-4-20250514-thinking-32k.

Blind head-to-head human votes, style controlled.

Berkeley BFCL

Not measured by Berkeley BFCL.

Function calling and tool use, single turn to multi turn and web search.

Price and context

$6.00

OpenRouter: $3.00 in, $15 out. Vercel AI Gateway: $3.00 in, $15 out Context window 200K tokens.

Nearby

The models either side of Claude Sonnet 4

  1. #69Kimi K2.7 Code47
  2. #70DeepSeek V3.1 Terminus47
  3. #71R147
  4. #72Claude Sonnet 446
  5. #73Grok 4.346
  6. #74MiniMax M2.146
  7. #75Qwen3.5-35B-A3B46

Questions about Claude Sonnet 4

How good is Claude Sonnet 4?
Claude Sonnet 4 ranks #72 of 126 models on the Rank.ai LLM leaderboard, with a consensus score of 46 out of 100 across 2 leaderboards.
Is Claude Sonnet 4 better than R1?
Not on the consensus: R1 scores 47 to Claude Sonnet 4's 46. Compare them source by source below, since the leaderboards test different things.
Is Claude Sonnet 4 better than Grok 4.3?
On the consensus, yes: 46 to 46.
How much does Claude Sonnet 4 cost?
$3.00 per million input tokens and $15 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $6.00 per million.
Is Claude Sonnet 4 good for coding?
It scores 37.6 on the Artificial Analysis Coding Index, placing it #45 for coding among the models on this leaderboard.

These models recommend brands. See if they name yours.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.