Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Gemma 4 31B and Hy4 preview, 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

Gemma 4 31B vs Hy4 preview

Live dataset updated 9/9/2026, 8:46:14 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Gemma 4 31B and Hy4 preview
Field
ModelCap position#27#26
Index score69.770.4
EvidenceMeasured3 public benchmark observations across 3 boardsMeasured9 reported rows against measured corpus ladders (38%); publisher-corpus-prior over 182 held-out anchors (12%); opens above measured predecessor tencent/hy3 on same-family ordering evidence (41%); 1 specialist-board observation at 2.5% support (9%); shrunk 1.2 toward the measured corpus
Input / 1M$0.09$0.834
Output / 1M$0.34$2.50
Pricing statusfreshfresh
Context262K1M
Providers131
Weight accessOpen weightsOpen weights

Decision facts

  • Gemma 4 31B is #27; Hy4 preview is #26 on the same current language board.
  • Index scores are 69.7 for Gemma 4 31B and 70.4 for Hy4 preview. 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 $0.34 for Gemma 4 31B and $2.50 for Hy4 preview. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.35 for Gemma 4 31B versus $2.92 for Hy4 preview. Gemma 4 31B costs 88.0% 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 Gemma 4 31B and 1,048,576 for Hy4 preview.
  • ModelCap currently lists 13 providers for Gemma 4 31B and 1 for Hy4 preview.

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.