Back to model catalog
Compare models
Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.
| Attribute | Hy4tencent/hy4 | Hy3tencent/hy3 |
|---|---|---|
| Specs | ||
| Context window | 1M | 262K |
| Max output | 66K | 131K |
| Input modalities | TextImage | Text |
| Output modalities | Text | Text |
| Capabilities | ||
| Streaming | Supported | Supported |
| Tool calling | Supported | Supported |
| Structured output (JSON) | Supported | Supported |
| Image input | Supported | Not supported |
| Thinking mode | Supported | Supported |
| Price / 1M tokens | ||
| Input | $ 0.96 | $ 0.16 |
| Output | $ 2.88 | $ 0.64 |
| Cache read | $ 0.048 | $ 0.040 |
| Cache write | $ 0.96 | $ 0.16 |
| What it is good at | ||
| Best for |
|
|
| Published benchmarks | ||
| Terminal-Bench 2.1pass_rate | — |
|
| Terminal-Bench 4.0pass_rate |
| — |
| BrowseComp (with tools)accuracy | — |
|
| Claw-Eval Generalpass3_rate | — |
|
| AutomationBench v1.0.6score |
| — |
| DeepSWE 1.1resolved_rate |
| — |
| ProgramBenchscore |
| — |
| SWE-Bench Multilingualresolved_rate | — |
|
| SWE-Bench Proresolved_rate | — |
|
| SWE-Bench Verifiedresolved_rate | — |
|
| OSWorld 2.1 (partial credit)score |
| — |
| AA-LCRscore | — |
|
| MMMU Proaccuracy |
| — |
| ZeroBench main (with tools)pass_at_5 |
| — |
| Humanity's Last Exam (with tools)accuracy | — |
|
| Humanity's Last Exam Full (with tools)accuracy |
| — |
| GPQA Diamondaccuracy | — |
|
| Terminal-Bench-Science 0.1accuracy |
| — |
| MCP Atlas Publicscore | — |
|