Claude Sonnet 4.6 (Max) vs GPT-5 mini (High)
Which is better for the money: Claude Sonnet 4.6 (Max) by Anthropic or GPT-5 mini (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
Claude Sonnet 4.6 (Max) scores 13.3 points higher (30.1 vs 16.8) but costs 26× as much to run the benchmark ($4925 vs $189; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 4.6 (Max) when you need intelligence above 16.8, and GPT-5 mini (High) when 16.8 is enough.
| Metric | Claude Sonnet 4.6 (Max) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 30.1 | 16.8 | −44.2% GPT-5 mini (High) is 44.2% less intelligent |
| Total AA cost (lower is better) | $4,924.80 | $188.66 | −96.2% GPT-5 mini (High) is 96.2% cheaper |
| End-to-end time (lower is better) | 101.20s | 60.90s | −39.8% GPT-5 mini (High) is 39.8% faster |
| Price per 1M tokens (in / out) | $3.00 / $15.0 | $0.25 / $2.00 | |
| Input modalities | Text, Image | Text, Image |
GPT-5 mini (High) vs Claude Sonnet 4.6 (Max): 44.2% less intelligence, 96.2% less cost to run the AA benchmark, and 39.8% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 4.6 (Max) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
Claude Sonnet 4.6 (Max)GPT-5 mini (High)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-sonnet-4-6-adaptive/gpt-5-mini · Markdown: /api/v1/compare/claude-sonnet-4-6-adaptive/gpt-5-mini?format=md · llms.txt · agent skill