StepFun: Step 3.7 Flash

RuntimeWire Composite Index

Score: 48.8 — ranked #18 overall (1/4 evaluations covered). View full rankings.

Community sentiment

Positive (+40) — 1 positive, 0 negative, 0 neutral across 1 community samples from X and the web, as of 2026-10-19.

Community mentions of Step 3.7 Flash emphasize its reliability, with users saying it “was super reliable.” Some comments also imply the model may no longer be available, noting it worked “while it lasted.”

• “@FrankYouChill @kilocode @StepFun_ai real step 3.7 flash was super reliable while it lasted 🙌” — X

RuntimeWire coverage

• StepFun launches a 600B agent model at $1 per million input tokens
• Claude Opus 5 (Fast) tops Newsroom Reliability v0.2 benchmark
• Z.ai GLM 5.3 Flash tops Editorial Craft benchmark at 0.94
• Open-weight models surge past closed rivals in Vercel token traffic
• The Week Open Weights Went Multimodal