DeepSeek R1 (Jan '25) vs Grok 4.3 (High)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Grok 4.3 (High) by SpaceXAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Grok 4.3 (High)
Grok 4.3 (High) vs DeepSeek R1 (Jan '25): 118.4% more intelligence, 21.2% less cost to run the AA benchmark, and 43.2% slower end-to-end.
| Metric | DeepSeek R1 (Jan '25) | Grok 4.3 (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 24.9 | +118.4% Grok 4.3 (High) is 2.2× more intelligent |
| Total AA cost (lower is better) | $460.74 | $363.24 | −21.2% Grok 4.3 (High) is 21.2% cheaper |
| End-to-end time (lower is better) | 20.16s | 28.87s | +43.2% Grok 4.3 (High) is 43.2% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $1.25 / $2.50 | |
| Input modalities | Text | Text, Image |
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.
- Grok 4.3 (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
DeepSeek R1 (Jan '25)Grok 4.3 (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/grok-4-3 · Markdown: /api/v1/compare/deepseek-r1-0120/grok-4-3?format=md · llms.txt · agent skill