Compare models
Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.
Claude Haiku 4.5GPT-5.1 (batch)
| Claude Haiku 4.5 Anthropic | GPT-5.1 (batch) OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $0.625 |
| Output $/1M | $5.00 | $5.00 |
| Blended $/1M (3:1) | $2.00 | $1.72 |
| Cache read $/1M | $0.10 | $0.063 |
| Cache write $/1M | $1.25 | — |
| Quality indices | ||
| Intelligence Index | 16.9 | 24.7 |
| Coding Index | 43.9 | 49.4 |
| Math Index | — | 94 |
| Agentic Index | 8 | — |
| Speed & latency | ||
| Output speed (tok/s) | — | 0 |
| Time to first token | — | 0s |
| Time to first answer token | — | 0s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | — | 87.0% |
| GPQA Diamond | — | 87.3% |
| Humanity's Last Exam | — | 28.5% |
| LiveCodeBench | — | 86.8% |
| AIME 2025 | — | 94.0% |
| IFBench | — | 72.9% |
| AA-LCR (Long Context Reasoning) | — | 80.0% |
| Terminal-Bench Hard | — | 45.5% |
| Terminal-Bench 2.1 | — | 52.4% |
| τ²-Bench (Telecom) | — | 81.9% |
| τ³-Bench Banking | — | 15.9% |
| Design Arena (Elo) | ||
| Website | 1,135 | 1,199 |
| UI components | 1,115 | 1,182 |
| Data viz | 1,139 | 1,219 |
| SVG | 1,049 | 1,173 |
| 3D | 1,101 | 1,089 |
| Game dev | 1,120 | 1,202 |
| Code categories | 1,130 | 1,186 |
| ASCII art | 1,159 | 1,137 |
| Specs | ||
| Context window | 200K | 400K |
| Max output tokens | 64K | 128K |
| Input modalities | text, image, file | image, text, file |
| Tokenizer | Claude | GPT |