DeepSeek R1 (Jan '25) vs GPT-6 Sol (High)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or GPT-6 Sol (High) by OpenAI? 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 (High) scores 31.0 points higher (42.4 vs 11.4) but costs 1.3× as much to run the benchmark ($605 vs $461; premium vs mid-range cost classes). Pick GPT-6 Sol (High) when the extra intelligence is worth the premium, otherwise DeepSeek R1 (Jan '25).
| Metric | DeepSeek R1 (Jan '25) | GPT-6 Sol (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 42.4 | +271.9% GPT-6 Sol (High) is 3.7× more intelligent |
| Total AA cost (lower is better) | $460.74 | $604.52 | +31.2% GPT-6 Sol (High) is 31.2% more expensive |
| End-to-end time (lower is better) | 20.14s | 15.56s | −22.7% GPT-6 Sol (High) is 22.7% faster |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $2.00 / $10.0 | |
| Input modalities | Text | Text, Image |
GPT-6 Sol (High) vs DeepSeek R1 (Jan '25): 271.9% more intelligence, 31.2% more cost to run the AA benchmark, and 22.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek R1 (Jan '25) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- GPT-6 Sol (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
DeepSeek R1 (Jan '25)GPT-6 Sol (High)Today'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/deepseek-r1-0120/gpt-6-sol-high · Markdown: /api/v1/compare/deepseek-r1-0120/gpt-6-sol-high?format=md · llms.txt · agent skill