← All Comparisons
Claude Haiku 4.5 vs GPT-5
A detailed comparison of Claude Haiku 4.5 (Anthropic) and GPT-5 (OpenAI) across pricing, performance, and features.
Pricing Comparison
| Metric | Claude Haiku 4.5 | GPT-5 | Difference |
|---|---|---|---|
| Input / 1M tokens | $0.80 | $1.25 | +56% |
| Output / 1M tokens | $4.00 | $10.00 | +150% |
| Context window | 200K | 128K | — |
| Max output | 8.192K | 16.384K | — |
Benchmark Comparison
| Benchmark | Claude Haiku 4.5 | GPT-5 |
|---|---|---|
| MMLU-Pro | 69.4% | 88.5% |
| HumanEval | 88.1% | 95% |
| GPQA | — | 73.5% |
Capabilities
| Capability | Claude Haiku 4.5 | GPT-5 |
|---|---|---|
| audio | ✗ | ✓ |
| code | ✓ | ✓ |
| reasoning | ✗ | ✓ |
| text | ✓ | ✓ |
| tool-use | ✓ | ✓ |
| vision | ✓ | ✓ |
Claude Haiku 4.5 Strengths
- ✓Very fast responses
- ✓Cheapest Anthropic option
- ✓Good for classification and extraction
Claude Haiku 4.5 Weaknesses
- ✗Weakest reasoning in the Claude family
- ✗Can struggle with nuanced instructions
GPT-5 Strengths
- ✓Strong all-around performance
- ✓Good price for flagship tier
- ✓Multimodal including audio
GPT-5 Weaknesses
- ✗128K context vs 200K+ for newer models
- ✗Codex variants better for pure coding
Quick Verdict
Best value: Claude Haiku 4.5 is the more affordable option at $0.8/$4 per 1M tokens.
Higher benchmarks: GPT-5 scores higher on average across available benchmarks (85.7% avg).
Larger context: Claude Haiku 4.5 supports 200K tokens.
Choose Claude Haiku 4.5 if cost matters most. Choose GPT-5 if you need the best possible quality for complex tasks.