Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Claude Haiku 4.5 and R1 0528, 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 Haiku 4.5 vs R1 0528

Live dataset updated 9/13/2026, 2:40:29 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Claude Haiku 4.5 and R1 0528
Field
R1 0528

DeepSeek

ModelCap position#62#59
Index score55.257.1
EvidenceMeasured3 public benchmark observations across 3 boardsMeasured2 public benchmark observations across 2 boards
Input / 1M$1.00$0.50
Output / 1M$5.00$2.15
Pricing statusfreshfresh
Context200K164K
Providers44
Weight accessAPI onlyOpen weights

Decision facts

  • Claude Haiku 4.5 is #62; R1 0528 is #59 on the same current language board.
  • Index scores are 55.2 for Claude Haiku 4.5 and 57.1 for R1 0528. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $5.00 for Claude Haiku 4.5 and $2.15 for R1 0528. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $4.50 for Claude Haiku 4.5 versus $2.08 for R1 0528. R1 0528 costs 53.9% 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 200,000 tokens for Claude Haiku 4.5 and 163,840 for R1 0528.
  • Weight access differs: Claude Haiku 4.5 is none; R1 0528 is open.

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.