GPT-6.1 Sol (Low) vs Mercury 2.5
Which is better for the money: GPT-6.1 Sol (Low) by OpenAI or Mercury 2.5 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Sol (Low) scores 29.8 points higher (42.1 vs 12.3) but costs 1.1× as much to run the benchmark ($250 vs $218; both mid-range class). Pick GPT-6.1 Sol (Low) when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | GPT-6.1 Sol (Low) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 42.1 | 12.3 | −70.8% Mercury 2.5 is 70.8% less intelligent |
| Total AA cost (lower is better) | $250.48 | $218.11 | −12.9% Mercury 2.5 is 12.9% cheaper |
| End-to-end time (lower is better) | 12.25s | 4.18s | −65.9% Mercury 2.5 is 65.9% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2.5 vs GPT-6.1 Sol (Low): 70.8% less intelligence, 12.9% less cost to run the AA benchmark, and 65.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Sol (Low) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
GPT-6.1 Sol (Low)Mercury 2.5Today'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-low/mercury-2-5 · Markdown: /api/v1/compare/gpt-6-1-sol-low/mercury-2-5?format=md · llms.txt · agent skill