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.
Gemini 3.1 Flash Lite PreviewGPT-5.6 Sol
| Gemini 3.1 Flash Lite Preview | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.25 | $5.00 |
| Output $/1M | $1.50 | $30.00 |
| Blended $/1M (3:1) | $0.563 | $11.25 |
| Cache read $/1M | $0.025 | $0.50 |
| Cache write $/1M | $0.083 | $6.25 |
| Quality indices | ||
| Intelligence Index | 25 | 58.9 |
| Coding Index | 34.7 | 77.4 |
| Math Index | — | — |
| Agentic Index | 6.2 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 326 | 70 |
| Time to first token | 4.89s | 112.90s |
| Time to first answer token | 4.89s | 112.90s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 82.2% | 94.1% |
| Humanity's Last Exam | 16.2% | 47.2% |
| SciCode | 41.9% | 56.1% |
| IFBench | 77.2% | 72.7% |
| AA-LCR (Long Context Reasoning) | 65.3% | 73.7% |
| Terminal-Bench Hard | 24.2% | 65.9% |
| Terminal-Bench 2.1 | 31.1% | 88.0% |
| τ²-Bench (Telecom) | 31.3% | 85.1% |
| τ³-Bench Banking | 8.7% | 33.0% |
| Design Arena (Elo) | ||
| Website | 1,109 | — |
| UI components | 1,113 | — |
| Data viz | 1,081 | — |
| SVG | 1,099 | — |
| 3D | 1,107 | — |
| Game dev | 1,090 | — |
| Code categories | 1,105 | — |
| ASCII art | 1,209 | — |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Max output tokens | 66K | 128K |
| Input modalities | text, image, video, file, audio | file, image, text |
| Tokenizer | Gemini | GPT |