Claude 4.5 Haiku (Reasoning) vs Claude Sonnet 5 (Medium)
Which is better for the money: Claude 4.5 Haiku (Reasoning) by Anthropic or Claude Sonnet 5 (Medium) by Anthropic? 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 5 (Medium) scores 11.2 points higher (28.1 vs 16.9) but costs 2.1× as much to run the benchmark ($1218 vs $594; both premium class). Pick Claude Sonnet 5 (Medium) when the extra intelligence is worth the premium, otherwise Claude 4.5 Haiku (Reasoning).
| Metric | Claude 4.5 Haiku (Reasoning) | Claude Sonnet 5 (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.9 | 28.1 | +66.3% Claude Sonnet 5 (Medi… is 66.3% more intelligent |
| Total AA cost (lower is better) | $594.08 | $1,218.17 | +105.1% Claude Sonnet 5 (Medi… is 2.1× more expensive |
| End-to-end time (lower is better) | 23.70s | 9.27s | −60.9% Claude Sonnet 5 (Medi… is 60.9% faster |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Sonnet 5 (Medium) vs Claude 4.5 Haiku (Reasoning): 66.3% more intelligence, 105.1% more cost to run the AA benchmark, and 60.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude 4.5 Haiku (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
- Claude Sonnet 5 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude 4.5 Haiku (Reasoning)Claude Sonnet 5 (Medium)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-haiku-reasoning/claude-sonnet-5-medium · Markdown: /api/v1/compare/claude-4-5-haiku-reasoning/claude-sonnet-5-medium?format=md · llms.txt · agent skill