Nex-N2-Pro
Nex AGI · 1 configuration
Intelligence28.2
Input / 1M$0.50
Output / 1M$2.50
Context262K
Tariff: SiliconFlow · Source: models-dev · 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 · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
28.2 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
89.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
33.7 %SciCodeCode generation for scientific research problems.
43.3 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
67.8 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
81.6 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
66.2 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
34.8 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output256K
Catalog listing date2026-06-02