token.app › Compare › Claude 3 Haiku vs GPT-5 Nano
Claude 3 Haiku vs GPT-5 Nano
GPT-5 Nano leads on 2 of 2 shared benchmarks. GPT-5 Nano is 3.6× cheaper per token on a blended 3:1 basis. GPT-5 Nano accepts the larger context window (400K).
Head to head
Blended price uses a 3:1 input:output mix
| Claude 3 Haiku | GPT-5 Nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input $/1M | $0.250 | $0.050 |
| Output $/1M | $1.25 | $0.400 |
| Blended $/1M | $0.500 | $0.138 |
| Context window | 200K | 400K |
| Max output | 4K | 128K |
| Released | Mar 2024 | Aug 2025 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 36.3% | 69.4% |
| OTIS Mock AIME | 1.8% | 81.1% |
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 Nano if…
- Costs less per token — $0.138 vs $0.500 blended
- Higher GPQA Diamond (69.4% vs 36.3%)
- Higher OTIS Mock AIME (81.1% vs 1.8%)
- Larger context window (400K)
- Newer model (released Aug 2025)
FAQ
Which is better, Claude 3 Haiku or GPT-5 Nano?
Across the 2 benchmarks both models have independently-run scores for, Claude 3 Haiku leads on 0 and GPT-5 Nano leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Claude 3 Haiku cheaper than GPT-5 Nano?
GPT-5 Nano is cheaper: $0.138 versus $0.500 per million tokens blended at 3:1 input:output. Input alone: $0.250 vs $0.050. Output alone: $1.25 vs $0.400.
What context windows do Claude 3 Haiku and GPT-5 Nano have?
Claude 3 Haiku: 200,000 tokens. GPT-5 Nano: 400,000 tokens.
Who makes Claude 3 Haiku and GPT-5 Nano?
Claude 3 Haiku is made by Anthropic. GPT-5 Nano is made by OpenAI.