Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Mistral Small 4 and gpt-oss-safeguard-20b, 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

Mistral Small 4 vs gpt-oss-safeguard-20b

Live dataset updated 9/15/2026, 9:19:37 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Mistral Small 4 and gpt-oss-safeguard-20b
Field
Mistral Small 4

Mistral AI

ModelCap position#117#167
Index score40.724.0
EvidenceMeasured1 public benchmark observation across 1 boardInheritedfinetune of openai/gpt-oss-20b · fp4 (100%)
Input / 1M$0.15$0.075
Output / 1M$0.60$0.30
Pricing statusfreshfresh
Context262K131K
Providers21
Weight accessOpen weightsOpen weights

Decision facts

  • Mistral Small 4 is #117; gpt-oss-safeguard-20b is #167 on the same current language board.
  • Index scores are 40.7 for Mistral Small 4 and 24.0 for gpt-oss-safeguard-20b. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Evidence differs: Mistral Small 4 is Measured; gpt-oss-safeguard-20b is Inherited.
  • Listed output price per 1M tokens is $0.60 for Mistral Small 4 and $0.30 for gpt-oss-safeguard-20b. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.60 for Mistral Small 4 versus $0.30 for gpt-oss-safeguard-20b. gpt-oss-safeguard-20b costs 50.0% 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 Mistral Small 4 and 131,072 for gpt-oss-safeguard-20b.
  • ModelCap currently lists 2 providers for Mistral Small 4 and 1 for gpt-oss-safeguard-20b.

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.