Head-to-head comparison
Inkling (Thinking Machines) and MiMo-V2.5 (Xiaomi) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.
Snapshot as of 22 September 2026
As of 22 September 2026, MiMo-V2.5 holds the stronger ModelCap Index position (#43 vs #46); and MiMo-V2.5 is 14.5× cheaper per output token ($0.28/1M vs $4.05/1M).
Evidence: 5 public benchmark observations across 5 boards · 2 public benchmark observations across 2 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.
Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.
Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.
MiMo-V2.5 ranks higher on the ModelCap Index as of 22 September 2026: #43 against #46. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
MiMo-V2.5 is cheaper on output tokens: $0.28/1M against $4.05/1M. Input tokens are $1.00/1M for Inkling and $0.14/1M for MiMo-V2.5. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $4.03 for Inkling versus $0.42 for MiMo-V2.5. MiMo-V2.5 costs 89.6% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
Both publish a 1M-token context window.
Arena coding: Inkling 1492, MiMo-V2.5 1491 — Inkling leads.
Inkling: Open weights. MiMo-V2.5: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.
ModelCap currently lists 3 API providers for Inkling and 6 for MiMo-V2.5, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.
Every figure comes from the sealed ModelCap dataset published 22 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.