modelgrep

Best StepFun Models for Agents

Quick answer · Updated June 2026

Step 3.7 Flash is the best StepFun model for agents, scoring 59.5 on the Artificial Analysis Agentic Index for tool use and multi-step task completion. Step 3.5 Flash (52.0) is next.

59.5Agentic
42.6Intelligence
92 t/sSpeed
$0.200Input /M
256KContext

AI models ranked by the Artificial Analysis Agentic Index — measuring multi-step tool use, planning and task completion (including Tau²-Bench). The best models for building autonomous agents and agentic workflows.

  1. 1S
    step-3.7-flash
    ReasoningToolsJSON+142.6 intel · $0.200/M · 92 t/s
    59.5
    Agentic
  2. 2S
    step-3.5-flash
    ReasoningToolsJSON37.8 intel · $0.090/M · 47 t/s
    52.0
    Agentic

Frequently asked

What is the best StepFun model for agents?

Step 3.7 Flash is the best StepFun model for agents, scoring 59.5 on the Artificial Analysis Agentic Index for tool use and multi-step task completion. Step 3.5 Flash (52.0) is next.

What's a good alternative to Step 3.7 Flash?

Step 3.5 Flash (52.0) is the closest alternative on this metric. See the full ranking above for the tradeoffs.

How many StepFun models are there?

modelgrep tracks 2 StepFun models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Step 3.7 Flash. 2 of them qualify for this ranking.

More StepFun rankings

All rankings