Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Claude Fable 5.2 and Claude Haiku 5.5, or choose any two current ranked language models. Compare capability evidence, price, context, provider availability, and weight access without pretending one field decides every use case.

Current public data

Claude Fable 5.2 vs Claude Haiku 5.5

Live dataset updated 11/19/2026, 5:34:52 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Claude Fable 5.2 and Claude Haiku 5.5
Field
ModelCap position#6#93
Index score84.258.3
EvidenceMeasuredpublisher-corpus-prior over 214 held-out anchors (16%); opens above measured predecessor anthropic/claude-fable-5 on same-family ordering evidence (58%); 3 specialist-board observations at 4.9% support (26%); shrunk 1.5 toward the measured corpusMeasured5 public benchmark observations across 5 boards
Input / 1M$8.00$0.10
Output / 1M$40.00$0.50
Pricing statusfreshfresh
Context1M1M
Providers35
Weight accessNo linked weightsNo linked weights

Decision facts

  • Claude Fable 5.2 is #6; Claude Haiku 5.5 is #93 on the same current language board.
  • Index scores are 84.2 for Claude Fable 5.2 and 58.3 for Claude Haiku 5.5. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $40.00 for Claude Fable 5.2 and $0.50 for Claude Haiku 5.5. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $36.00 for Claude Fable 5.2 versus $0.45 for Claude Haiku 5.5. Claude Haiku 5.5 costs 98.8% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
  • Published context is 1,000,000 tokens for Claude Fable 5.2 and 1,000,000 for Claude Haiku 5.5.
  • ModelCap currently lists 3 providers for Claude Fable 5.2 and 5 for Claude Haiku 5.5.

These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.

Each comparison page is a permanent, shareable URL with the same live figures as this tool: ModelCap Index position, API pricing, context window, provider count, weight access and every shared benchmark board.