Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Kimi K2.7 Code and Step3 VL 10B, 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

Kimi K2.7 Code vs Step3 VL 10B

Live dataset updated 9/9/2026, 10:25:31 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Kimi K2.7 Code and Step3 VL 10B
Field
Kimi K2.7 Code

Moonshot AI

Step3 VL 10B

Stepfun Ai

ModelCap position#50#49
Index score59.560.0
EvidenceMeasured2 public benchmark observations across 2 boardsEstimatedglobal-corpus-prior over 183 held-out anchors (17%); launch card against 2 resolved peers on 4 rows (83%); exceeds every named peer on 3 of 4 rows; no cross-lab optimism probe available; shrunk 1.4 toward the measured corpus
Input / 1M$0.71Unavailable
Output / 1M$3.50Unavailable
Pricing statusfreshunavailable
Context262K
Providers140
Weight accessRestricted licenseOpen weights

Decision facts

  • Kimi K2.7 Code is #50; Step3 VL 10B is #49 on the same current language board.
  • Index scores are 59.5 for Kimi K2.7 Code and 60.0 for Step3 VL 10B. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Evidence differs: Kimi K2.7 Code is Measured; Step3 VL 10B is Estimated.
  • Weight access differs: Kimi K2.7 Code is restricted; Step3 VL 10B is open.
  • ModelCap currently lists 14 providers for Kimi K2.7 Code and 0 for Step3 VL 10B.

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.