Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Qwen3.5 397B A17B and Qwen3 Coder 30B A3B Instruct, 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

Qwen3.5 397B A17B vs Qwen3 Coder 30B A3B Instruct

Live dataset updated 10/1/2026, 9:09:05 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Qwen3.5 397B A17B and Qwen3 Coder 30B A3B Instruct
Field
ModelCap position#43#99
Index score68.054.1
EvidenceMeasured3 public benchmark observations across 3 boardsEstimatedpublisher-corpus-prior over 231 held-out anchors (6%); launch card against 3 resolved peers on 4 rows (94%); no cross-lab optimism probe available
Input / 1M$0.55$0.07
Output / 1M$3.50$0.28
Pricing statusfreshfresh
Context262K262K
Providers104
Weight accessOpen weightsOpen weights

Decision facts

  • Qwen3.5 397B A17B is #43; Qwen3 Coder 30B A3B Instruct is #99 on the same current language board.
  • Index scores are 68.0 for Qwen3.5 397B A17B and 54.1 for Qwen3 Coder 30B A3B Instruct. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
  • Evidence differs: Qwen3.5 397B A17B is Measured; Qwen3 Coder 30B A3B Instruct is Estimated.
  • Listed output price per 1M tokens is $3.50 for Qwen3.5 397B A17B and $0.28 for Qwen3 Coder 30B A3B Instruct. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $2.85 for Qwen3.5 397B A17B versus $0.28 for Qwen3 Coder 30B A3B Instruct. Qwen3 Coder 30B A3B Instruct costs 90.2% 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 Qwen3.5 397B A17B and 262,144 for Qwen3 Coder 30B A3B Instruct.
  • ModelCap currently lists 10 providers for Qwen3.5 397B A17B and 4 for Qwen3 Coder 30B A3B Instruct.

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.