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 Opus 4.6GPT-5.5 (batch)
| Claude Opus 4.6 Anthropic | GPT-5.5 (batch) OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $2.50 |
| Output $/1M | $25.00 | $15.00 |
| Blended $/1M (3:1) | $10.00 | $5.63 |
| Cache read $/1M | $0.50 | $0.25 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 26.4 | 38.4 |
| Coding Index | — | 74.9 |
| Math Index | — | — |
| Agentic Index | — | 36.4 |
| Speed & latency | ||
| Output speed (tok/s) | 0 | 0 |
| Time to first token | 0s | 0s |
| Time to first answer token | 0s | 0s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 84.0% | 93.5% |
| Humanity's Last Exam | 19.1% | 45.8% |
| SciCode | — | 55.8% |
| IFBench | 44.6% | 75.9% |
| AA-LCR (Long Context Reasoning) | 67.0% | 84.3% |
| Terminal-Bench Hard | 48.5% | 60.6% |
| Terminal-Bench 2.1 | — | 84.3% |
| τ²-Bench (Telecom) | 84.8% | 93.9% |
| τ³-Bench Banking | — | 39.0% |
| Design Arena (Elo) | ||
| Website | 1,303 | 1,269 |
| Web apps | 1,219 | 1,132 |
| Full-stack | 1,229 | 1,099 |
| Mobile apps | 1,238 | 1,171 |
| Android native | 1,216 | 1,175 |
| UI components | 1,300 | 1,273 |
| Data viz | 1,296 | 1,273 |
| SVG | 1,251 | 1,260 |
| 3D | 1,303 | 1,226 |
| Game dev | 1,301 | 1,320 |
| Agentic game dev | 1,215 | 1,179 |
| Godot game dev | — | 1,183 |
| HTML slides | — | 1,070 |
| PPTX slides | — | 1,157 |
| Python→PPTX slides | — | 1,152 |
| Agentic slides | — | 1,150 |
| Agentic HTML slides | — | 1,084 |
| Agentic slides (HTML) | — | 1,077 |
| Agentic slides (Python PPTX) | — | 1,155 |
| Code categories | 1,304 | 1,274 |
| ASCII art | 1,273 | 1,276 |
| Specs | ||
| Context window | 1M | 1.05M |
| Max output tokens | 128K | 128K |
| Input modalities | text, image, file | file, image, text |
| Tokenizer | Claude | GPT |