Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Mistral Small 4 and Qwen3 235B A22B Thinking 2507, 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 Qwen3 235B A22B Thinking 2507

Live dataset updated 9/19/2026, 11:04:59 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Mistral Small 4 and Qwen3 235B A22B Thinking 2507
Field
Mistral Small 4

Mistral AI

ModelCap position#91#90
Index score50.450.5
EvidenceMeasured1 public benchmark observation across 1 boardMeasured2 public benchmark observations across 2 boards
Input / 1M$0.15$0.23
Output / 1M$0.60$2.30
Pricing statusfreshfresh
Context262K131K
Providers13
Weight accessOpen weightsOpen weights

Decision facts

  • Mistral Small 4 is #91; Qwen3 235B A22B Thinking 2507 is #90 on the same current language board.
  • Index scores are 50.4 for Mistral Small 4 and 50.5 for Qwen3 235B A22B Thinking 2507. 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 $0.60 for Mistral Small 4 and $2.30 for Qwen3 235B A22B Thinking 2507. 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 $1.61 for Qwen3 235B A22B Thinking 2507. Mistral Small 4 costs 62.7% 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 Qwen3 235B A22B Thinking 2507.
  • ModelCap currently lists 1 providers for Mistral Small 4 and 3 for Qwen3 235B A22B Thinking 2507.

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.