Skip to content
ModelCap

Model decision surface

Compare AI models

Start with R1 0528 and Nemotron 3 Labs Ultra Math RL, 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

R1 0528 vs Nemotron 3 Labs Ultra Math RL

Live dataset updated 9/9/2026, 9:50:24 PM UTC

Open 1200×630 evidence receipt
Factual comparison of R1 0528 and Nemotron 3 Labs Ultra Math RL
Field
R1 0528

DeepSeek

ModelCap position#50#52
Index score58.857.6
EvidenceMeasured2 public benchmark observations across 2 boardsInheritedfinetune of nvidia/nemotron-3-ultra-550b-a55b · bf16 (100%)
Input / 1M$0.50Unavailable
Output / 1M$2.15Unavailable
Pricing statusfreshunavailable
Context164K
Providers40
Weight accessOpen weightsRestricted license

Decision facts

  • R1 0528 is #50; Nemotron 3 Labs Ultra Math RL is #52 on the same current language board.
  • Index scores are 58.8 for R1 0528 and 57.6 for Nemotron 3 Labs Ultra Math RL. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Evidence differs: R1 0528 is Measured; Nemotron 3 Labs Ultra Math RL is Inherited.
  • Weight access differs: R1 0528 is open; Nemotron 3 Labs Ultra Math RL is restricted.
  • ModelCap currently lists 4 providers for R1 0528 and 0 for Nemotron 3 Labs Ultra Math RL.

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.