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 Fable 5.1 (batch)GPT-4.1
| Claude Fable 5.1 (batch) Anthropic | GPT-4.1 OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $2.00 |
| Output $/1M | $25.00 | $8.00 |
| Blended $/1M (3:1) | $10.00 | $3.50 |
| Cache read $/1M | $0.125 | $0.50 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 53.4 | 12.7 |
| Coding Index | 81.6 | — |
| Math Index | — | 34.7 |
| Agentic Index | 57.9 | — |
| Speed & latency | ||
| Output speed (tok/s) | 73 | 0 |
| Time to first token | 153.32s | 0s |
| Time to first answer token | 153.32s | 0s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | — | 80.6% |
| GPQA Diamond | 93.7% | 66.6% |
| Humanity's Last Exam | 59.1% | 4.2% |
| LiveCodeBench | — | 45.7% |
| SciCode | 63.1% | — |
| MATH-500 | — | 91.3% |
| AIME | — | 43.7% |
| AIME 2025 | — | 34.7% |
| IFBench | — | 43.0% |
| AA-LCR (Long Context Reasoning) | 85.3% | 68.3% |
| Terminal-Bench Hard | — | 13.6% |
| Terminal-Bench 2.1 | 91.4% | — |
| τ²-Bench (Telecom) | — | 47.1% |
| τ³-Bench Banking | 47.2% | — |
| Design Arena (Elo) | ||
| Website | 1,323 | 1,051 |
| Web apps | 1,336 | — |
| Full-stack | 1,336 | — |
| UI components | 1,336 | 1,016 |
| Data viz | 1,369 | 1,117 |
| SVG | 1,347 | — |
| 3D | 1,425 | 878 |
| Game dev | 1,404 | 1,103 |
| Python→PPTX slides | 1,328 | — |
| Code categories | 1,346 | 1,041 |
| ASCII art | 1,330 | — |
| Specs | ||
| Context window | 1M | 1.05M |
| Max output tokens | 128K | 33K |
| Input modalities | text, image, file | image, text, file |
| Tokenizer | Claude | GPT |