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 2.5 Flash (batch)GPT-5.6 Sol
| Gemini 2.5 Flash (batch) | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.15 | $2.00 |
| Output $/1M | $1.25 | $10.00 |
| Blended $/1M (3:1) | $0.425 | $4.00 |
| Cache read $/1M | $0.03 | $0.20 |
| Cache write $/1M | — | $2.50 |
| Quality indices | ||
| Intelligence Index | 9.9 | 47 |
| Coding Index | — | 77.4 |
| Math Index | 60.3 | — |
| Agentic Index | — | 50.2 |
| Speed & latency | ||
| Output speed (tok/s) | 0 | 65 |
| Time to first token | 0s | 64.46s |
| Time to first answer token | 0s | 64.46s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | 80.9% | — |
| GPQA Diamond | 68.3% | 94.1% |
| Humanity's Last Exam | 4.7% | 49.5% |
| LiveCodeBench | 49.5% | — |
| SciCode | — | 57.1% |
| MATH-500 | 93.2% | — |
| AIME | 50.0% | — |
| AIME 2025 | 60.3% | — |
| IFBench | 39.0% | 72.7% |
| AA-LCR (Long Context Reasoning) | 49.9% | 84.0% |
| Terminal-Bench Hard | 12.1% | 65.9% |
| Terminal-Bench 2.1 | — | 88.0% |
| τ²-Bench (Telecom) | 14.9% | 85.1% |
| τ³-Bench Banking | — | 44.3% |
| Design Arena (Elo) | ||
| Website | 1,127 | — |
| UI components | 1,108 | — |
| Data viz | 1,149 | — |
| SVG | 1,043 | — |
| 3D | 1,100 | — |
| Game dev | 1,089 | — |
| Code categories | 1,119 | — |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Max output tokens | 66K | 128K |
| Input modalities | file, image, text, audio, video | file, image, text |
| Tokenizer | Gemini | GPT |