DeepSeek V4.1 Flash 1017 (Max) vs Step 5 Preview
Which is better for the money: DeepSeek V4.1 Flash 1017 (Max) by DeepSeek or Step 5 Preview by StepFun? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick DeepSeek V4.1 Flash 1017 (Max)
Step 5 Preview vs DeepSeek V4.1 Flash 1017 (Max): 3.1% less intelligence, 167.7% more cost to run the AA benchmark, and 18.4% faster end-to-end.
| Metric | DeepSeek V4.1 Flash 1017 (Max) | Step 5 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 45.1 | 43.7 | −3.1% Step 5 Preview is 3.1% less intelligent |
| Total AA cost (lower is better) | $444.60 | $1,190.26 | +167.7% Step 5 Preview is 2.7× more expensive |
| End-to-end time (lower is better) | 14.71s | 12.01s | −18.4% Step 5 Preview is 18.4% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $1.00 / $2.70 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- DeepSeek V4.1 Flash 1017 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Step 5 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
DeepSeek V4.1 Flash 1017 (Max)Step 5 PreviewToday's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v4-1-flash-1017/step-5 · Markdown: /api/v1/compare/deepseek-v4-1-flash-1017/step-5?format=md · llms.txt · agent skill