BlogLLM Benchmark Scores as Published, Side by Side

MiMo-V2.6-Flash: Benchmark Scores as Published

Every result the catalog holds for MiMo-V2.6-Flash: 16 tests in 5 areas, from 3 pages. All were printed by Xiaomi itself. Each number is as printed; nothing is ranked or rescored.

Developer XiaomiReleased 2026-09-21Input TextOutput TextWeights OpenData version 2026103001, as of 2026-10-30

Knowledge Work

TestValuePrinted bySetup as printed
AutomationBench52.3%Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19-
JobBench61.2Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19-

Agentic Coding

Computer Use

TestValuePrinted bySetup as printed
OSWorld-Verified80.8%Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19-

Cybersecurity

Tool Use and Workflows

Price

API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.

PriceValuePrinted bySetup as printed
Input$0.14Xiaomi, Xiaomi MiMo API pricingchecked 2026-10-19Region: international
Cached input$0.0028Xiaomi, Xiaomi MiMo API pricingchecked 2026-10-19Region: international
Output$0.28Xiaomi, Xiaomi MiMo API pricingchecked 2026-10-19Region: international
Input, batch$0.07Xiaomi, Xiaomi MiMo API pricingchecked 2026-10-19Region: international
Cached input, batch$0.0014Xiaomi, Xiaomi MiMo API pricingchecked 2026-10-19Region: international
Output, batch$0.14Xiaomi, Xiaomi MiMo API pricingchecked 2026-10-19Region: international
Cost per taskVals AI, USD, lower is better$0.56Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27Harness: OpenHands

More from Xiaomi

Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.