Claude 4.5 Haiku (Reasoning) vs GPT-5.6 Luna (Max)
Which is better for the money: Claude 4.5 Haiku (Reasoning) by Anthropic or GPT-5.6 Luna (Max) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick GPT-5.6 Luna (Max)
GPT-5.6 Luna (Max) vs Claude 4.5 Haiku (Reasoning): 120.7% more intelligence, 46.1% less cost to run the AA benchmark, and 368.2% slower end-to-end.
| Metric | Claude 4.5 Haiku (Reasoning) | GPT-5.6 Luna (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.9 | 37.3 | +120.7% GPT-5.6 Luna (Max) is 2.2× more intelligent |
| Total AA cost (lower is better) | $594.08 | $319.93 | −46.1% GPT-5.6 Luna (Max) is 46.1% cheaper |
| End-to-end time (lower is better) | 24.36s | 114.06s | +368.2% GPT-5.6 Luna (Max) is 368.2% slower |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $0.20 / $1.20 | |
| Input modalities | Text, Image | Text, Image |
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.
- GPT-5.6 Luna (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Claude 4.5 Haiku (Reasoning)GPT-5.6 Luna (Max)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/gpt-5-6-luna · Markdown: /api/v1/compare/claude-4-5-haiku-reasoning/gpt-5-6-luna?format=md · llms.txt · agent skill