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 K3 (batch)GPT-5.6 Sol
| Kimi K3 (batch) Moonshot AI | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $3.00 | $2.00 |
| Output $/1M | $15.00 | $10.00 |
| Blended $/1M (3:1) | $6.00 | $4.00 |
| Cache read $/1M | $0.30 | $0.20 |
| Cache write $/1M | — | $2.50 |
| Quality indices | ||
| Intelligence Index | 43.6 | 47 |
| Coding Index | 76.2 | 77.4 |
| Math Index | — | — |
| Agentic Index | 50 | 50.2 |
| Speed & latency | ||
| Output speed (tok/s) | — | 65 |
| Time to first token | — | 64.46s |
| Time to first answer token | — | 64.46s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | — | 94.1% |
| Humanity's Last Exam | — | 49.5% |
| SciCode | — | 57.1% |
| IFBench | — | 72.7% |
| AA-LCR (Long Context Reasoning) | — | 84.0% |
| Terminal-Bench Hard | — | 65.9% |
| Terminal-Bench 2.1 | — | 88.0% |
| τ²-Bench (Telecom) | — | 85.1% |
| τ³-Bench Banking | — | 44.3% |
| Design Arena (Elo) | ||
| Website | 1,352 | — |
| Web apps | 1,309 | — |
| Full-stack | 1,333 | — |
| Mobile apps | 1,279 | — |
| Android native | 1,259 | — |
| UI components | 1,371 | — |
| Data viz | 1,358 | — |
| SVG | 1,330 | — |
| 3D | 1,425 | — |
| Game dev | 1,407 | — |
| Agentic game dev | 1,252 | — |
| Godot game dev | 1,199 | — |
| HTML slides | 1,259 | — |
| Python→PPTX slides | 1,273 | — |
| Code categories | 1,386 | — |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Max output tokens | 944K | 128K |
| Input modalities | text, image, video | file, image, text |
| Tokenizer | Other | GPT |