GPT-6 Sol (Non-reasoning) vs Mercury 2.5
Which is better for the money: GPT-6 Sol (Non-reasoning) by OpenAI or Mercury 2.5 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GPT-6 Sol (Non-reasoning) scores 16.2 points higher (28.5 vs 12.3) but costs 2.1× as much to run the benchmark ($449 vs $218; both mid-range class). Pick GPT-6 Sol (Non-reasoning) when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | GPT-6 Sol (Non-reasoning) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 28.5 | 12.3 | −56.8% Mercury 2.5 is 56.8% less intelligent |
| Total AA cost (lower is better) | $449.37 | $218.11 | −51.5% Mercury 2.5 is 51.5% cheaper |
| End-to-end time (lower is better) | 5.83s | 4.33s | −25.7% Mercury 2.5 is 25.7% 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 Sol (Non-reasoning): 56.8% less intelligence, 51.5% less cost to run the AA benchmark, and 25.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Sol (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
GPT-6 Sol (Non-reasoning)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-sol-non-reasoning/mercury-2-5 · Markdown: /api/v1/compare/gpt-6-sol-non-reasoning/mercury-2-5?format=md · llms.txt · agent skill