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-4o (2024-08-06)
| Gemini 3.6 Flash | GPT-4o (2024-08-06) OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.50 | $2.50 |
| Output $/1M | $7.50 | $10.00 |
| Blended $/1M (3:1) | $3.00 | $4.38 |
| Cache read $/1M | $0.15 | $1.25 |
| Cache write $/1M | $0.083 | — |
| Quality indices | ||
| Intelligence Index | 50.1 | 9.6 |
| Coding Index | 69.2 | — |
| Math Index | — | — |
| Agentic Index | 38.7 | — |
| Speed & latency | ||
| Output speed (tok/s) | 311 | 93 |
| Time to first token | 12.80s | 0.54s |
| Time to first answer token | 12.80s | 0.54s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 92.8% | 52.1% |
| Humanity's Last Exam | 38.3% | 2.9% |
| LiveCodeBench | — | 31.7% |
| SciCode | 52.7% | 33.1% |
| MATH-500 | — | 79.5% |
| AIME | — | 11.7% |
| IFBench | — | 36.0% |
| AA-LCR (Long Context Reasoning) | 69.7% | 35.0% |
| Terminal-Bench Hard | — | 8.3% |
| Terminal-Bench 2.1 | 77.5% | — |
| τ²-Bench (Telecom) | — | 28.9% |
| τ³-Bench Banking | 24.5% | — |
| Design Arena (Elo) | ||
| Website | 1,332 | — |
| Specs | ||
| Context window | 1.05M | 128K |
| Max output tokens | 66K | 16K |
| Input modalities | text, image, video, file, audio | text, image, file |
| Tokenizer | Gemini | GPT |