GPT-4.1 mini vs Trinity Large Thinking
Which is better for the money: GPT-4.1 mini by OpenAI or Trinity Large Thinking by Arcee AI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-19.
Trade-off
Verdict
Depends on your budget
Trinity Large Thinking scores 3.9 points higher (18.7 vs 14.8) but costs 4.0× as much to run the benchmark ($255 vs $64.2; both mid-range class). They are not alternatives at one budget: pick Trinity Large Thinking when you need intelligence above 14.8, and GPT-4.1 mini when 14.8 is enough.
| Metric | GPT-4.1 mini | Trinity Large Thinking | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 14.8 | 18.7 | +26.4% Trinity Large Thinking is 26.4% more intelligent |
| Total AA cost (lower is better) | $64.23 | $254.72 | +296.6% Trinity Large Thinking is 4.0× more expensive |
| End-to-end time (lower is better) | 5.84s | 14.08s | +141.1% Trinity Large Thinking is 141.1% slower |
| Price per 1M tokens (in / out) | $0.40 / $1.60 | $0.23 / $0.88 | |
| Input modalities | Not reported | Not reported |
Trinity Large Thinking vs GPT-4.1 mini: 26.4% more intelligence, 296.6% more cost to run the AA benchmark, and 141.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-4.1 mini is off the frontier: at the same or lower cost, GPT-5.6 Luna (high) scores 47.00 for $55.0.
- Trinity Large Thinking is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
GPT-4.1 miniTrinity 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/gpt-4-1-mini/trinity-large-thinking · Markdown: /api/v1/compare/gpt-4-1-mini/trinity-large-thinking?format=md · llms.txt · agent skill