DeepSeek R1 (Jan '25) vs GPT-6.1 Sol (Xhigh)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or GPT-6.1 Sol (Xhigh) by OpenAI? 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 (Xhigh) scores 39.6 points higher (51.0 vs 11.4) but costs 1.4× as much to run the benchmark ($662 vs $461; premium vs mid-range cost classes). Pick GPT-6.1 Sol (Xhigh) when the extra intelligence is worth the premium, otherwise DeepSeek R1 (Jan '25).
| Metric | DeepSeek R1 (Jan '25) | GPT-6.1 Sol (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 51.0 | +347.4% GPT-6.1 Sol (Xhigh) is 4.5× more intelligent |
| Total AA cost (lower is better) | $460.74 | $662.28 | +43.7% GPT-6.1 Sol (Xhigh) is 43.7% more expensive |
| End-to-end time (lower is better) | 19.17s | 143.74s | +649.8% GPT-6.1 Sol (Xhigh) is 649.8% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $2.00 / $10.0 | |
| Input modalities | Text | Text, Image |
GPT-6.1 Sol (Xhigh) vs DeepSeek R1 (Jan '25): 347.4% more intelligence, 43.7% more cost to run the AA benchmark, and 649.8% slower 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-6.1 Sol (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
DeepSeek R1 (Jan '25)GPT-6.1 Sol (Xhigh)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-6-1-sol-xhigh · Markdown: /api/v1/compare/deepseek-r1-0120/gpt-6-1-sol-xhigh?format=md · llms.txt · agent skill