← Back to explorer
AnthropicReleased 2026-06

Claude Fable 5

Anthropic's frontier agentic coding and knowledge-work flagship. Leads Artificial Analysis Intelligence Index and SWE-bench Verified in this snapshot.

Context
1M
Speed
58 t/s
Price /M
$10 / $50
Access
api

When to use it

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

Watch-outs

Premium pricing; availability can lag announcements. Overkill for simple chat.

CodingAgentsWritingScience

Benchmarks

Arena Elo1525

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

AA Intelligence Index60

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

SWE-bench Verified95%

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

GPQA Diamond92.6%

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

MMLU-Pro91.5%

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

Humanity's Last Exam53.3%

Frontier closed-ended academic difficulty across many domains.

More from Anthropic

  • 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
  • Claude Sonnet 4

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

    AA 48

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

Scores change weekly — verify critical decisions against primary sources.