Skip to content
ModelCap

Model decision surface

Compare AI models

Start with gpt-oss-20b and Qwen3 30B A3B, 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

gpt-oss-20b vs Qwen3 30B A3B

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

Open 1200×630 evidence receipt
Factual comparison of gpt-oss-20b and Qwen3 30B A3B
Field
ModelCap position#131#132
Index score28.528.3
EvidenceMeasured3 public benchmark observations across 3 boardsMeasured2 public benchmark observations across 2 boards
Input / 1M$0.03$0.12
Output / 1M$0.13$0.50
Pricing statusfreshfresh
Context131K131K
Providers122
Weight accessOpen weightsOpen weights

Decision facts

  • gpt-oss-20b is #131; Qwen3 30B A3B is #132 on the same current language board.
  • Index scores are 28.5 for gpt-oss-20b and 28.3 for Qwen3 30B A3B. 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 $0.13 for gpt-oss-20b and $0.50 for Qwen3 30B A3B. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.13 for gpt-oss-20b versus $0.49 for Qwen3 30B A3B. gpt-oss-20b costs 74.5% 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 131,072 tokens for gpt-oss-20b and 131,072 for Qwen3 30B A3B.
  • ModelCap currently lists 12 providers for gpt-oss-20b and 2 for Qwen3 30B A3B.

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.