GPT-6.1 Terra (Non-reasoning) vs Step 5 Preview
Which is better for the money: GPT-6.1 Terra (Non-reasoning) by OpenAI or Step 5 Preview by StepFun? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
Step 5 Preview scores 10.2 points higher (43.7 vs 33.5) but costs 7.8× as much to run the benchmark ($1190 vs $154; premium vs mid-range cost classes). They are not alternatives at one budget: pick Step 5 Preview when you need intelligence above 33.5, and GPT-6.1 Terra (Non-reasoning) when 33.5 is enough.
| Metric | GPT-6.1 Terra (Non-reasoning) | Step 5 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 33.5 | 43.7 | +30.4% Step 5 Preview is 30.4% more intelligent |
| Total AA cost (lower is better) | $153.58 | $1,190.26 | +675.0% Step 5 Preview is 7.8× more expensive |
| End-to-end time (lower is better) | 6.51s | 14.87s | +128.4% Step 5 Preview is 128.4% slower |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $1.00 / $2.70 | |
| Input modalities | Text, Image | Text, Image |
Step 5 Preview vs GPT-6.1 Terra (Non-reasoning): 30.4% more intelligence, 675.0% more cost to run the AA benchmark, and 128.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Terra (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Step 5 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
GPT-6.1 Terra (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/gpt-6-1-terra-non-reasoning/step-5 · Markdown: /api/v1/compare/gpt-6-1-terra-non-reasoning/step-5?format=md · llms.txt · agent skill