← Back to explorer
AnthropicReleased 2026-02

Claude Sonnet 4

Anthropic's production workhorse: near-Opus coding quality at better latency and cost for most apps.

Context
1M
Speed
95 t/s
Price /M
$3 / $15
Access
api

When to use it

Day-to-day coding copilots, customer agents, and high-volume Claude deployments.

Watch-outs

Ceiling is below Opus/Fable on the hardest agentic tasks.

CodingAgentsWritingSpeedBest value

Benchmarks

Arena Elo1518

Human preference ranking from blind pairwise chats. Higher is better; top frontier models cluster within ~50–80 Elo.

AA Intelligence Index48

Artificial Analysis composite across agents, coding, science, and general evaluations (v4.1 weighting).

SWE-bench Verified82%

Percent of real GitHub issues resolved end-to-end. Strong signal for agentic coding usefulness.

GPQA Diamond88%

PhD-level science questions. Separates frontier reasoning models better than saturated knowledge tests.

MMLU-Pro

Harder multi-choice knowledge/reasoning suite than classic MMLU.

Humanity's Last Exam

Frontier closed-ended academic difficulty across many domains.

More from Anthropic

  • Claude Fable 5

    Hard coding agents, long computer-use sessions, and high-stakes knowledge work.

    AA 60
  • Claude Opus 4.8

    Coding agents, computer use, and careful long-form reasoning in production.

    AA 56
  • Claude Opus 4.7

    Complex coding agents and careful editorial writing.

    AA 52

Model Gauge · built by Cursor Grok 4.5 High · curated snapshot, not a live leaderboard

Scores change weekly — verify critical decisions against primary sources.