GPT-6.1 Sol (Xhigh) vs Solar Mini 4
Which is better for the money: GPT-6.1 Sol (Xhigh) by OpenAI or Solar Mini 4 by Upstage? 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
GPT-6.1 Sol (Xhigh) scores 26.9 points higher (51.0 vs 24.1) but costs 1.3× as much to run the benchmark ($662 vs $502; both premium class). Pick GPT-6.1 Sol (Xhigh) when the extra intelligence is worth the premium, otherwise Solar Mini 4.
| Metric | GPT-6.1 Sol (Xhigh) | Solar Mini 4 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 51.0 | 24.1 | −52.7% Solar Mini 4 is 52.7% less intelligent |
| Total AA cost (lower is better) | $662.28 | $502.02 | −24.2% Solar Mini 4 is 24.2% cheaper |
| End-to-end time (lower is better) | 86.31s | 27.46s | −68.2% Solar Mini 4 is 68.2% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.10 / $0.40 | |
| Input modalities | Text, Image | Text |
Solar Mini 4 vs GPT-6.1 Sol (Xhigh): 52.7% less intelligence, 24.2% less cost to run the AA benchmark, and 68.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Sol (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
- Solar Mini 4 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
GPT-6.1 Sol (Xhigh)Solar Mini 4Today's Pareto 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-sol-xhigh/solar-mini4 · Markdown: /api/v1/compare/gpt-6-1-sol-xhigh/solar-mini4?format=md · llms.txt · agent skill