Claude 4.5 Sonnet (Reasoning) vs GPT-5.4 mini (Xhigh)
Which is better for the money: Claude 4.5 Sonnet (Reasoning) by Anthropic or GPT-5.4 mini (Xhigh) 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-5.4 mini (Xhigh) scores 3.4 points higher (24.1 vs 20.7) but costs 1.0× as much to run the benchmark ($1524 vs $1501; both premium class). Pick GPT-5.4 mini (Xhigh) when the extra intelligence is worth the premium, otherwise Claude 4.5 Sonnet (Reasoning).
| Metric | Claude 4.5 Sonnet (Reasoning) | GPT-5.4 mini (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.7 | 24.1 | +16.4% GPT-5.4 mini (Xhigh) is 16.4% more intelligent |
| Total AA cost (lower is better) | $1,501.22 | $1,524.02 | +1.5% GPT-5.4 mini (Xhigh) is 1.5% more expensive |
| End-to-end time (lower is better) | 21.58s | 109.06s | +405.4% GPT-5.4 mini (Xhigh) is 405.4% slower |
| Price per 1M tokens (in / out) | $3.00 / $15.0 | $0.75 / $4.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-5.4 mini (Xhigh) vs Claude 4.5 Sonnet (Reasoning): 16.4% more intelligence, 1.5% more cost to run the AA benchmark, and 405.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude 4.5 Sonnet (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- GPT-5.4 mini (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude 4.5 Sonnet (Reasoning)GPT-5.4 mini (Xhigh)Today'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/claude-4-5-sonnet-thinking/gpt-5-4-mini · Markdown: /api/v1/compare/claude-4-5-sonnet-thinking/gpt-5-4-mini?format=md · llms.txt · agent skill