Artificial Analysis pre-release evals put Claude Fable 5.1 at 66 on the Intelligence Index at max effort—ahead of Opus 5 (63), Fable 5 (62), GPT-5.6 Sol (61), and Grok 4.6 (61). Even with cache reads cut from $1 to $0.25 per million tokens, ~1.7x more output tokens leave max-effort tasks at about $3.76, ~20% above Fable 5; xhigh scores 65 at about $2.72 per task.

Key Takeaways

  • ✓Score 66 is the highest Intelligence Index AA has measured, ahead of Opus 5, Fable 5, GPT-5.6 Sol, and Grok 4.6.
  • ✓The cache-read cut saves ~$1.40/task but higher output tokens still leave max effort ~20% costlier than Fable 5.
  • ✓xhigh effort (~65 at ~$2.72/task) is the better cost/quality tradeoff versus max.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
Claude 3.7 Sonnet (Hybrid Reasoning) · in: $3 / out: $15
Compare Plans↗
🛠️ Ecosystem & IDERules
Claude Code (Anthropic) · Cursor Composer (Agent Mode)
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextArtificial Analysis Releases HealthBench & MLCR-AA: Exposing Severe Verbosity Bias in Medical AI Rankings
Read Now→