DeepSeek V4 Pro 0813 (Non-reasoning) vs Step 5 Preview
Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek or Step 5 Preview by StepFun? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Step 5 Preview scores 23.3 points higher (43.7 vs 20.4) but costs 2.6× as much to run the benchmark ($1190 vs $451; premium vs mid-range cost classes). Pick Step 5 Preview when the extra intelligence is worth the premium, otherwise DeepSeek V4 Pro 0813 (Non-reasoning).
| Metric | DeepSeek V4 Pro 0813 (Non-reasoning) | Step 5 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 43.7 | +114.2% Step 5 Preview is 2.1× more intelligent |
| Total AA cost (lower is better) | $450.76 | $1,190.26 | +164.1% Step 5 Preview is 2.6× more expensive |
| End-to-end time (lower is better) | 6.81s | 12.06s | +77.1% Step 5 Preview is 77.1% slower |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $1.00 / $2.70 | |
| Input modalities | Text | Text, Image |
Step 5 Preview vs DeepSeek V4 Pro 0813 (Non-reasoning): 114.2% more intelligence, 164.1% more cost to run the AA benchmark, and 77.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Non-reasoning) 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 Pro 0813 (Non-reasoning)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-pro-non-reasoning/step-5 · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/step-5?format=md · llms.txt · agent skill