Claude Haiku 5.5 (Medium) vs GPT-5.6 Luna (Non-reasoning)
Which is better for the money: Claude Haiku 5.5 (Medium) by Anthropic or GPT-5.6 Luna (Non-reasoning) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
Claude Haiku 5.5 (Medium) scores 19.0 points higher (34.5 vs 15.5) but costs 2.5× as much to run the benchmark ($56.4 vs $23.0; mid-range vs budget cost classes). Pick Claude Haiku 5.5 (Medium) when the extra intelligence is worth the premium, otherwise GPT-5.6 Luna (Non-reasoning).
| Metric | Claude Haiku 5.5 (Medium) | GPT-5.6 Luna (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.5 | 15.5 | −55.1% GPT-5.6 Luna (Non-rea… is 55.1% less intelligent |
| Total AA cost (lower is better) | $56.36 | $22.97 | −59.2% GPT-5.6 Luna (Non-rea… is 59.2% cheaper |
| End-to-end time (lower is better) | 14.74s | 5.14s | −65.1% GPT-5.6 Luna (Non-rea… is 65.1% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.20 / $1.20 | |
| Input modalities | Text, Image | Text, Image |
GPT-5.6 Luna (Non-reasoning) vs Claude Haiku 5.5 (Medium): 55.1% less intelligence, 59.2% less cost to run the AA benchmark, and 65.1% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Medium) is on today's frontier: nothing is both smarter and cheaper.
- GPT-5.6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Claude Haiku 5.5 (Medium)GPT-5.6 Luna (Non-reasoning)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-medium/gpt-5-6-luna-non-reasoning · Markdown: /api/v1/compare/claude-haiku-5-5-medium/gpt-5-6-luna-non-reasoning?format=md · llms.txt · agent skill