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.
DeepSeek V3 0324GPT-5.6 Sol
| DeepSeek V3 0324 DeepSeek | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.27 | $5.00 |
| Output $/1M | $1.12 | $30.00 |
| Blended $/1M (3:1) | $0.483 | $11.25 |
| Cache read $/1M | $0.135 | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 15.4 | 58.9 |
| Coding Index | 21.2 | 77.4 |
| Math Index | 41 | — |
| Agentic Index | 1.5 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 0 | 67 |
| Time to first token | 0s | 120.38s |
| Time to first answer token | 0s | 120.38s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | 81.9% | — |
| GPQA Diamond | 65.5% | 94.1% |
| Humanity's Last Exam | 5.2% | 47.2% |
| LiveCodeBench | 40.5% | — |
| SciCode | 35.8% | 56.1% |
| MATH-500 | 94.2% | — |
| AIME | 52.0% | — |
| AIME 2025 | 41.0% | — |
| IFBench | 41.0% | 72.7% |
| AA-LCR (Long Context Reasoning) | 41.0% | 73.7% |
| Terminal-Bench Hard | 15.2% | 65.9% |
| Terminal-Bench 2.1 | 13.9% | 88.0% |
| τ²-Bench (Telecom) | 47.1% | 85.1% |
| τ³-Bench Banking | 4.5% | 33.0% |
| Specs | ||
| Context window | 164K | 1.05M |
| Max output tokens | 66K | 128K |
| Input modalities | text | file, image, text |
| Tokenizer | DeepSeek | GPT |