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 3.8 Flash (batch)GPT-5.6 Sol
| Gemini 3.8 Flash (batch) | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.375 | $2.00 |
| Output $/1M | $1.88 | $10.00 |
| Blended $/1M (3:1) | $0.75 | $4.00 |
| Cache read $/1M | $0.037 | $0.20 |
| Cache write $/1M | $0.042 | $2.50 |
| Quality indices | ||
| Intelligence Index | 40.9 | 47 |
| Coding Index | 76.3 | 77.4 |
| Math Index | — | — |
| Agentic Index | 40.2 | 50.2 |
| Speed & latency | ||
| Output speed (tok/s) | 327 | 65 |
| Time to first token | 12.22s | 64.46s |
| Time to first answer token | 12.22s | 64.46s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 95.3% | 94.1% |
| Humanity's Last Exam | 47.8% | 49.5% |
| SciCode | 56.6% | 57.1% |
| IFBench | — | 72.7% |
| AA-LCR (Long Context Reasoning) | 81.3% | 84.0% |
| Terminal-Bench Hard | — | 65.9% |
| Terminal-Bench 2.1 | 87.6% | 88.0% |
| τ²-Bench (Telecom) | — | 85.1% |
| τ³-Bench Banking | 44.9% | 44.3% |
| Design Arena (Elo) | ||
| Website | 1,315 | — |
| Web apps | 1,256 | — |
| Full-stack | 1,250 | — |
| Mobile apps | 1,259 | — |
| UI components | 1,338 | — |
| Data viz | 1,264 | — |
| 3D | 1,324 | — |
| Game dev | 1,340 | — |
| Python→PPTX slides | 1,176 | — |
| Code categories | 1,323 | — |
| 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 |