Claude 3 Haiku vs GPT-5.6 Luna
GPT-5.6 Luna is cheaper on output tokens, while GPT-5.6 Luna offers a larger context window. Choose Claude 3 Haiku or GPT-5.6 Luna based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude 3 Haiku | GPT-5.6 Luna |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input / 1M tokens | $0.25 | $0.20 |
| Output / 1M tokens | $1.25 | $1.20 |
| Context window | 200K | 1.1M |
| Parameters | — | — |
| Open weights | — | — |
| Released | — | — |
| SWE-bench Verified score | 40.6 | — |
| LMArena (Chatbot Arena) Elo score | 1195 | 1431 |
| LMArena Vision Elo score | 950 | 1258 |
| GPQA Diamond score | 36.3 | 91.6 |
| Epoch Capabilities Index score | 118 | 156 |
| LMArena WebDev Elo score | — | 1518 |
FAQ
Is Claude 3 Haiku or GPT-5.6 Luna cheaper?
GPT-5.6 Luna is cheaper on output tokens ($1.20 vs $1.25 per 1M).
Which has the larger context window, Claude 3 Haiku or GPT-5.6 Luna?
GPT-5.6 Luna has the larger context window (1.1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.