AI ScoreboardFrontend & Coding Index← Back to rankings

MODEL PROFILE / EDITION 2026.09

Claude Fable 5

Teams pinned to Fable 5 snapshots for reproducibility until they migrate to 5.1

AnthropicRank 11Confidence ANo prior snapshot
78.9

Balanced model evidence score; rank 11. No rank delta is shown because there is no prior numeric snapshot.

Best for

Teams pinned to Fable 5 snapshots for reproducibility until they migrate to 5.1

Price & access

$10 in / $50 out per 1M; cache read $1.00 (4x Fable 5.1's $0.25), cache write $12.50

Evidence summary

Bedrock card, Anthropic pricing page, two human-preference boards and two third-party leaderboards all cover it; only the Legacy-vs-Active status differs between Anthropic and AWS.

Edition status

No prior snapshot. Tracked in the September 2026 baseline.

Strengths

  • SWE-bench Pro 80.0% and Verified 95% keep it in the top handful for code correctness
  • FrontierSWE 88.2 is the best value in Z.ai's cross-vendor table
  • Very well-sampled Arena row (8,017 votes, +/-8) and Design Arena rank 9
  • 1M multimodal context with 128K output

Tradeoffs

  • Same $10/$50 price as Fable 5.1 but 4x more expensive cache reads and lower scores
  • Now labelled Legacy on Anthropic's pricing page
  • Terminal-Bench 4.0 44.5% trails Fable 5.1's 55.8%
  • TTFT 108.60 s

Score profile

visual 80 · code 94 · agentic 88 · debug 85 · context 92 · speed 56 · value 36

Linked evidence

Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗Evidence source 7 ↗
Compare this model on the full scoreboard

Use the same published data, filters, and side-by-side metrics.

Open comparison view →