Step 3.7 Flash vs Trinity Large Thinking
Which is better for the money: Step 3.7 Flash by StepFun or Trinity Large Thinking by Arcee AI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-17.
Trade-off
Verdict
Depends on your budget
Step 3.7 Flash scores 12.2 points higher (30.9 vs 18.7) but costs 1.3× as much to run the benchmark ($320 vs $255; both mid-range class). Pick Step 3.7 Flash when the extra intelligence is worth the premium, otherwise Trinity Large Thinking.
| Metric | Step 3.7 Flash | Trinity Large Thinking | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 30.9 | 18.7 | −39.5% Trinity Large Thinking is 39.5% less intelligent |
| Total AA cost (lower is better) | $319.97 | $254.72 | −20.4% Trinity Large Thinking is 20.4% cheaper |
| End-to-end time (lower is better) | 19.27s | 13.49s | −30.0% Trinity Large Thinking is 30.0% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.15 | $0.23 / $0.88 | |
| Input modalities | Not reported | Not reported |
Trinity Large Thinking vs Step 3.7 Flash: 39.5% less intelligence, 20.4% less cost to run the AA benchmark, and 30.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Step 3.7 Flash is off the frontier: at the same or lower cost, Gemini 3.7 Flash (medium) scores 53.40 for $278.
- Trinity Large Thinking is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
Step 3.7 FlashTrinity Large ThinkingToday'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/step-3-7-flash/trinity-large-thinking · Markdown: /api/v1/compare/step-3-7-flash/trinity-large-thinking?format=md · llms.txt · agent skill