Skip to content
llmwaves

Claude Sonnet 4

Anthropic · released May 22, 2025

ProprietaryReasoningTool useVision

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...

Specification

Context window
1M
Max output
64K
Knowledge cutoff
Jan 31, 2025
Parameters
Undisclosed
Licence
Proprietary
Serving providers
2
Moderated
Yes
Uptime
100.0%

Intelligence

26.0

69th percentile

Coding

Coding Index

Agentic

17.6

Agentic Index

Output speed

41 t/s

Median across providers

Latency

863ms

Time to first token

Cost per task

$1.35

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    83.7%
  • GPQA Diamond
    68.3%
  • τ²-bench (Telecom)
    52.3%
  • AA-LCR (long context)
    45.7%
  • IFBench
    45.4%
  • LiveCodeBench
    44.9%
  • AIME 2025
    38.0%
  • SciCode
    37.3%
  • Terminal-Bench Hard
    27.3%
  • Humanity's Last Exam
    4.3%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro83.7%
GPQA Diamond68.3%
τ²-bench (Telecom)52.3%
AA-LCR (long context)45.7%
IFBench45.4%
LiveCodeBench44.9%
AIME 202538.0%
SciCode37.3%
Terminal-Bench Hard27.3%
Humanity's Last Exam4.3%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
o4 Mini High26.1
o4 Mini26.1
Claude Sonnet 426.0
Claude Opus 426.0
Gemini 2.5 Pro25.9
GPT-5 Mini25.8
Gemini 3.1 Flash Lite25.6
Gemini 3.1 Flash Lite Preview25.6

Percentile among all indexed models

Intelligence69th
Agentic29th
Mathematics38th
Terminal work69th
Arena Elo57th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$3
Output / 1M tokens
$15
Cached input / 1M
$0.3
Blended 3:1
$6

One task, estimated

$1.35

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,195
Win rate
57.8%
Strongest at
3D scenes
Tournaments
1,573

Elo by category

Dot position on a 1,125–1,200 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
3D scenes119557.8%
Game development118054.8%
Data visualisation117955.8%
Websites116852.4%
UI components116458.0%
SVG112551.1%