Qwen3.7 Plus vs Step 5 Preview
Which is better for the money: Qwen3.7 Plus by Alibaba or Step 5 Preview by StepFun? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Step 5 Preview scores 18.5 points higher (43.7 vs 25.2) but costs 2.8× as much to run the benchmark ($1190 vs $428; premium vs mid-range cost classes). Pick Step 5 Preview when the extra intelligence is worth the premium, otherwise Qwen3.7 Plus.
| Metric | Qwen3.7 Plus | Step 5 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.2 | 43.7 | +73.4% Step 5 Preview is 73.4% more intelligent |
| Total AA cost (lower is better) | $427.73 | $1,190.26 | +178.3% Step 5 Preview is 2.8× more expensive |
| End-to-end time (lower is better) | 46.20s | 12.01s | −74.0% Step 5 Preview is 74.0% faster |
| Price per 1M tokens (in / out) | $0.40 / $1.60 | $1.00 / $2.70 | |
| Input modalities | Text, Image, Video | Text, Image |
Step 5 Preview vs Qwen3.7 Plus: 73.4% more intelligence, 178.3% more cost to run the AA benchmark, and 74.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Qwen3.7 Plus 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.
Qwen3.7 PlusStep 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/qwen3-7-plus/step-5 · Markdown: /api/v1/compare/qwen3-7-plus/step-5?format=md · llms.txt · agent skill