List your company

Step Prediction on Pen-Strategist (test)

82.87AccuracyStep Model
40.115651.215362.31573.4147May 6, 2026

Evaluation results

MethodLinks
Step Model2026.0582.8780
Gemini 2.5 Flash2026.0564.5268
Claude 4.5 sonnet2026.0563.4466
GPT 4.12026.0562.7865
Gemini 2.0 Flash2026.0561.2967
GPT-5-mini2026.0559.6665
Claude 3 Haiku2026.0555.4353
GPT-4o-mini2026.0554.8354
LLaMA-3.1-8B2026.0551.0954
GPT-3.5-turbo2026.0541.7645