Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Trinity Large Thinking and Mistral Small 4, 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

Trinity Large Thinking vs Mistral Small 4

Live dataset updated 9/10/2026, 3:47:06 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Trinity Large Thinking and Mistral Small 4
Field
Mistral Small 4

Mistral AI

ModelCap position#105#104
Index score40.440.8
EvidenceMeasured3 public benchmark observations across 3 boardsMeasured1 public benchmark observation across 1 board
Input / 1M$0.25$0.15
Output / 1M$0.80$0.60
Pricing statusfreshfresh
Context262K262K
Providers12
Weight accessRestricted licenseOpen weights

Decision facts

  • Trinity Large Thinking is #105; Mistral Small 4 is #104 on the same current language board.
  • Index scores are 40.4 for Trinity Large Thinking and 40.8 for Mistral Small 4. 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 $0.80 for Trinity Large Thinking and $0.60 for Mistral Small 4. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.90 for Trinity Large Thinking versus $0.60 for Mistral Small 4. Mistral Small 4 costs 33.3% 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 262,144 tokens for Trinity Large Thinking and 262,144 for Mistral Small 4.
  • Weight access differs: Trinity Large Thinking is restricted; Mistral Small 4 is open.
  • ModelCap currently lists 1 providers for Trinity Large Thinking and 2 for Mistral Small 4.

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.