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 3.6 FlashGPT-4.1
| Gemini 3.6 Flash | GPT-4.1 OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.50 | $2.00 |
| Output $/1M | $7.50 | $8.00 |
| Blended $/1M (3:1) | $3.00 | $3.50 |
| Cache read $/1M | $0.15 | $0.50 |
| Cache write $/1M | $0.083 | — |
| Quality indices | ||
| Intelligence Index | 50.1 | 19.4 |
| Coding Index | 69.2 | — |
| Math Index | — | 34.7 |
| Agentic Index | 38.7 | — |
| Speed & latency | ||
| Output speed (tok/s) | 301 | 149 |
| Time to first token | 11.80s | 0.56s |
| Time to first answer token | 11.80s | 0.56s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | — | 80.6% |
| GPQA Diamond | 92.8% | 66.6% |
| Humanity's Last Exam | 38.3% | 4.6% |
| LiveCodeBench | — | 45.7% |
| SciCode | 52.7% | 38.1% |
| MATH-500 | — | 91.3% |
| AIME | — | 43.7% |
| AIME 2025 | — | 34.7% |
| IFBench | — | 43.0% |
| AA-LCR (Long Context Reasoning) | 69.7% | 61.0% |
| Terminal-Bench Hard | — | 13.6% |
| Terminal-Bench 2.1 | 77.5% | — |
| τ²-Bench (Telecom) | — | 47.1% |
| τ³-Bench Banking | 24.5% | — |
| Design Arena (Elo) | ||
| Website | 1,332 | 1,066 |
| UI components | — | 1,043 |
| Data viz | — | 1,140 |
| 3D | — | 908 |
| Game dev | — | 1,138 |
| Code categories | — | 1,059 |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Max output tokens | 66K | 33K |
| Input modalities | text, image, video, file, audio | image, text, file |
| Tokenizer | Gemini | GPT |