MiMo-V2.5-Pro
Xiaomi · 2 thinking configurations
Intelligence26.0
Input / 1M$0.44
Output / 1M$0.87
Context1M
Tariff: Xiaomi · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 1 without both values
Selected: thinking thinking · Click a point to switch configuration
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
26.0 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
86.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
35.7 %SciCodeCode generation for scientific research problems.
50.6 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
65.2 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
94.2 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
79.9 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
22.4 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed32.0 tok/s
First token2.47 s
Maximum output131.1K
Catalog listing date2026-04-22