token.app › Compare › Claude 3 Haiku vs GPT-5.6 Luna
Claude 3 Haiku vs GPT-5.6 Luna
GPT-5.6 Luna leads on 2 of 2 shared benchmarks. GPT-5.6 Luna is 2.2× cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).
Head to head
Blended price uses a 3:1 input:output mix
| Claude 3 Haiku | GPT-5.6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input $/1M | $0.250 | $0.100 |
| Output $/1M | $1.25 | $0.600 |
| Blended $/1M | $0.500 | $0.225 |
| Context window | 200K | 1.1M |
| Max output | 4K | 128K |
| Released | Mar 2024 | Jul 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 36.3% | 91.6% |
| OTIS Mock AIME | 1.8% | 98.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Claude 3 Haiku if…
- No clear advantage on the data we hold.
Choose GPT-5.6 Luna if…
- Costs less per token — $0.225 vs $0.500 blended
- Higher GPQA Diamond (91.6% vs 36.3%)
- Higher OTIS Mock AIME (98.3% vs 1.8%)
- Larger context window (1.1M)
- Newer model (released Jul 2026)
FAQ
Which is better, Claude 3 Haiku or GPT-5.6 Luna?
Across the 2 benchmarks both models have independently-run scores for, Claude 3 Haiku leads on 0 and GPT-5.6 Luna leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Claude 3 Haiku cheaper than GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.225 versus $0.500 per million tokens blended at 3:1 input:output. Input alone: $0.250 vs $0.100. Output alone: $1.25 vs $0.600.
What context windows do Claude 3 Haiku and GPT-5.6 Luna have?
Claude 3 Haiku: 200,000 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Claude 3 Haiku and GPT-5.6 Luna?
Claude 3 Haiku is made by Anthropic. GPT-5.6 Luna is made by OpenAI.