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.
Gemma 4 31BGPT-5.6 Sol
| Gemma 4 31B | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.12 | $5.00 |
| Output $/1M | $0.37 | $30.00 |
| Blended $/1M (3:1) | $0.182 | $11.25 |
| Cache read $/1M | — | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 29.4 | 58.9 |
| Coding Index | 43.4 | 77.4 |
| Math Index | — | — |
| Agentic Index | 14.4 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 35 | 70 |
| Time to first token | 0.98s | 112.90s |
| Time to first answer token | 50.29s | 112.90s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 85.7% | 94.1% |
| Humanity's Last Exam | 22.7% | 47.2% |
| SciCode | 43.4% | 56.1% |
| IFBench | 75.6% | 72.7% |
| AA-LCR (Long Context Reasoning) | 62.0% | 73.7% |
| Terminal-Bench Hard | 36.4% | 65.9% |
| Terminal-Bench 2.1 | 43.4% | 88.0% |
| τ²-Bench (Telecom) | 59.9% | 85.1% |
| τ³-Bench Banking | 15.1% | 33.0% |
| Specs | ||
| Context window | 262K | 1.05M |
| Max output tokens | 16K | 128K |
| Input modalities | image, text, video | file, image, text |
| Tokenizer | Gemma | GPT |