The Trace Manifest
Subscribe
Corrections Subscribe

Claude Fable 5

Anthropic · Closed · 5

Strongest model for long-horizon repository coding. Excels at complex multi-file work.

Status
active
Release date
2026-06-15
Parameters
unknown
Context window
200K
Modalities
text,code,image
Capabilities recorded
tool use, structured output, API
Last verified
2026-07-20

Reviewed use cases

  • large codebase work
  • long-running agents

Recorded limitations

  • Higher latency than GPT-5.6 Sol

Benchmark Performance

69.7 / 100   TRACE Aggregate Score

TRACE Score 69.7/100 based on 2 benchmarks. 1 independent run (weighted 3×). 1 vendor-reported run (weighted 1×). Last updated 01/07/2026.

BenchmarkScoreProvenanceDateSource
SWE-bench Verified 80.0% Vendor 01/07/2026 Source
LMSYS Chatbot Arena ~1330 Independent 01/07/2026 Source

Pricing is omitted until provider-model pricing rows have their own completed review and publication state.