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 4.6Gemini 3.1 Pro Preview
| Claude Opus 4.6 Anthropic | Gemini 3.1 Pro Preview | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $2.00 |
| Output $/1M | $25.00 | $12.00 |
| Blended $/1M (3:1) | $10.00 | $4.50 |
| Cache read $/1M | $0.50 | $0.20 |
| Cache write $/1M | $6.25 | $0.375 |
| Quality indices | ||
| Intelligence Index | 37.8 | 46.5 |
| Coding Index | — | 68.8 |
| Math Index | — | — |
| Agentic Index | — | 21.4 |
| Speed & latency | ||
| Output speed (tok/s) | 54 | 135 |
| Time to first token | 1.89s | 19.70s |
| Time to first answer token | 1.89s | 19.70s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 84.0% | 94.1% |
| Humanity's Last Exam | 18.6% | 44.7% |
| SciCode | 45.7% | 58.9% |
| IFBench | 44.6% | 77.1% |
| AA-LCR (Long Context Reasoning) | 58.3% | 72.7% |
| Terminal-Bench Hard | 48.5% | 53.8% |
| Terminal-Bench 2.1 | — | 73.8% |
| τ²-Bench (Telecom) | 84.8% | 95.6% |
| τ³-Bench Banking | — | 16.5% |
| Design Arena (Elo) | ||
| Website | 1,323 | 1,278 |
| Web apps | 1,261 | 1,182 |
| Full-stack | 1,279 | 1,127 |
| Mobile apps | 1,280 | 1,167 |
| Android native | 1,195 | 1,038 |
| UI components | 1,336 | 1,309 |
| Data viz | 1,322 | 1,262 |
| SVG | 1,274 | 1,334 |
| 3D | 1,335 | 1,291 |
| Game dev | 1,337 | 1,258 |
| Agentic game dev | — | 1,128 |
| Godot game dev | — | 1,159 |
| HTML slides | — | 1,202 |
| PPTX slides | — | 1,110 |
| Python→PPTX slides | — | 1,109 |
| Agentic slides | — | 1,112 |
| Agentic HTML slides | — | 1,226 |
| Agentic slides (HTML) | — | 1,219 |
| Agentic slides (Python PPTX) | — | 1,107 |
| Code categories | 1,327 | 1,274 |
| ASCII art | 1,298 | 1,312 |
| Specs | ||
| Context window | 1M | 1.05M |
| Max output tokens | 128K | 66K |
| Input modalities | text, image, file | audio, file, image, text, video |
| Tokenizer | Claude | Gemini |