Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Command A and Mercury 2.5, 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

Command A vs Mercury 2.5

Live dataset updated 9/15/2026, 8:34:26 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Command A and Mercury 2.5
Field
Command A

Cohere

Mercury 2.5

Inception Labs

ModelCap position#133#128
Index score35.137.3
EvidenceMeasured2 public benchmark observations across 2 boardsEstimatedglobal-corpus-prior over 193 held-out anchors (23%); opens from measured predecessor inception/mercury-2 (77%); shrunk 4.4 up toward the measured corpus
Input / 1M$2.50$0.04
Output / 1M$10.00$0.15
Pricing statusfreshfresh
Context256K260K
Providers11
Weight accessGated accessAPI only

Decision facts

  • Command A is #133; Mercury 2.5 is #128 on the same current language board.
  • Index scores are 35.1 for Command A and 37.3 for Mercury 2.5. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Evidence differs: Command A is Measured; Mercury 2.5 is Estimated.
  • Listed output price per 1M tokens is $10.00 for Command A and $0.15 for Mercury 2.5. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $10.00 for Command A versus $0.15 for Mercury 2.5. Mercury 2.5 costs 98.5% 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 256,000 tokens for Command A and 260,000 for Mercury 2.5.
  • Weight access differs: Command A is gated; Mercury 2.5 is none.

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.