Claude Haiku 5.5 (Max) vs Gemini 4 Carbon (Medium)
Which is better for the money: Claude Haiku 5.5 (Max) by Anthropic or Gemini 4 Carbon (Medium) by Google? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-03.
Trade-off
Verdict
Depends on your budget
Gemini 4 Carbon (Medium) scores 21.5 points higher (57.7 vs 36.2) but costs 17× as much to run the benchmark ($5903 vs $339; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 4 Carbon (Medium) when you need intelligence above 36.2, and Claude Haiku 5.5 (Max) when 36.2 is enough.
| Metric | Claude Haiku 5.5 (Max) | Gemini 4 Carbon (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 36.2 | 57.7 | +59.4% Gemini 4 Carbon (Medi… is 59.4% more intelligent |
| Total AA cost (lower is better) | $339.47 | $5,903.03 | +1638.9% Gemini 4 Carbon (Medi… is 17× more expensive |
| End-to-end time (lower is better) | 345.57s | 11.62s | −96.6% Gemini 4 Carbon (Medi… is 96.6% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $4.00 / $20.0 | |
| Input modalities | Text, Image | Text, Image, Speech, Video |
Gemini 4 Carbon (Medium) vs Claude Haiku 5.5 (Max): 59.4% more intelligence, 1638.9% more cost to run the AA benchmark, and 96.6% 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, GPT-6.1 Terra (High) scores 42.30 for $267.
- Gemini 4 Carbon (Medium) is on today's frontier: nothing is both smarter and cheaper.
Claude Haiku 5.5 (Max)Gemini 4 Carbon (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-haiku-5-5/gemini-4-carbon-medium · Markdown: /api/v1/compare/claude-haiku-5-5/gemini-4-carbon-medium?format=md · llms.txt · agent skill