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.
Kimi K2.6GPT-5.6 Sol
| Kimi K2.6 Moonshot AI | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.684 | $5.00 |
| Output $/1M | $3.42 | $30.00 |
| Blended $/1M (3:1) | $1.37 | $11.25 |
| Cache read $/1M | $0.144 | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 44.2 | 58.9 |
| Coding Index | 61.8 | 77.4 |
| Math Index | — | — |
| Agentic Index | 30.3 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | — | 67 |
| Time to first token | — | 120.38s |
| Time to first answer token | — | 120.38s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | — | 94.1% |
| Humanity's Last Exam | — | 47.2% |
| SciCode | — | 56.1% |
| 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% |
| Design Arena (Elo) | ||
| Website | 1,304 | — |
| Web apps | 1,268 | — |
| Full-stack | 1,216 | — |
| Mobile apps | 1,248 | — |
| Android native | 1,294 | — |
| UI components | 1,305 | — |
| Data viz | 1,295 | — |
| SVG | 1,225 | — |
| 3D | 1,333 | — |
| Game dev | 1,307 | — |
| Agentic game dev | 1,157 | — |
| Godot game dev | 1,168 | — |
| HTML slides | 1,229 | — |
| PPTX slides | 1,181 | — |
| Python→PPTX slides | 1,180 | — |
| Agentic slides | 1,187 | — |
| Agentic HTML slides | 1,248 | — |
| Agentic slides (HTML) | 1,252 | — |
| Agentic slides (Python PPTX) | 1,186 | — |
| Code categories | 1,311 | — |
| ASCII art | 1,192 | — |
| Specs | ||
| Context window | 262K | 1.05M |
| Max output tokens | 262K | 128K |
| Input modalities | text, image | file, image, text |
| Tokenizer | Other | GPT |