Claude Haiku 5.5 (Max) vs GPT-5 mini (High)
Which is better for the money: Claude Haiku 5.5 (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 2026-10-26.
Trade-off
Verdict
Depends on your budget
Claude Haiku 5.5 (Max) scores 26.6 points higher (43.4 vs 16.8) but costs 1.8× as much to run the benchmark ($330 vs $189; both mid-range class). Pick Claude Haiku 5.5 (Max) when the extra intelligence is worth the premium, otherwise GPT-5 mini (High).
| Metric | Claude Haiku 5.5 (Max) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 16.8 | −61.3% GPT-5 mini (High) is 61.3% less intelligent |
| Total AA cost (lower is better) | $330.25 | $188.66 | −42.9% GPT-5 mini (High) is 42.9% cheaper |
| End-to-end time (lower is better) | 327.94s | 67.32s | −79.5% GPT-5 mini (High) is 79.5% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.25 / $2.00 | |
| Input modalities | Text, Image | Text, Image |
GPT-5 mini (High) vs Claude Haiku 5.5 (Max): 61.3% less intelligence, 42.9% less cost to run the AA benchmark, and 79.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- 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 Haiku 5.5 (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-haiku-5-5/gpt-5-mini · Markdown: /api/v1/compare/claude-haiku-5-5/gpt-5-mini?format=md · llms.txt · agent skill