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.
GPT-5.6 SolSonar
| GPT-5.6 Sol OpenAI | Sonar Perplexity | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $1.00 |
| Output $/1M | $30.00 | $1.00 |
| Blended $/1M (3:1) | $11.25 | $1.00 |
| Cache read $/1M | $0.50 | — |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 58.9 | 9.5 |
| Coding Index | 77.4 | — |
| Math Index | — | — |
| Agentic Index | 54 | — |
| Speed & latency | ||
| Output speed (tok/s) | 70 | 0 |
| Time to first token | 112.90s | 0s |
| Time to first answer token | 112.90s | 0s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | — | 68.9% |
| GPQA Diamond | 94.1% | 47.1% |
| Humanity's Last Exam | 47.2% | 7.3% |
| LiveCodeBench | — | 29.5% |
| SciCode | 56.1% | 22.9% |
| MATH-500 | — | 81.7% |
| AIME | — | 48.7% |
| IFBench | 72.7% | — |
| AA-LCR (Long Context Reasoning) | 73.7% | — |
| Terminal-Bench Hard | 65.9% | — |
| Terminal-Bench 2.1 | 88.0% | — |
| τ²-Bench (Telecom) | 85.1% | — |
| τ³-Bench Banking | 33.0% | — |
| Specs | ||
| Context window | 1.05M | 127K |
| Max output tokens | 128K | — |
| Input modalities | file, image, text | text, image |
| Tokenizer | GPT | Other |