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.

Hy4 Preview Add a modelChat with this model

Attribute	Hy4 Previewtencent/hy4-preview
Specs
Context window	1M
Max output	66K
Input modalities	Text
Output modalities	Text
Capabilities
Streaming	Supported
Tool calling	Supported
Structured output (JSON)	Supported
Image input	Not supported
Thinking mode	Supported
Price / 1M tokens
Input	$ 0.96
Output	$ 2.88
Cache read	$ 0.048
Cache write	$ 0.96
What it is good at
Best for	Agentic coding Long-context work Office and analysis Scientific research
Published benchmarks
Terminal-Bench 2.1pass_rate	85.4%effort high · Claude Code(setup not fully disclosed)
Agents' Last Exam (CLI)score	22.8%effort high · Claude Code(setup not fully disclosed)
SWE-Bench Multilingualresolved_rate	82.9%effort high · SWE-agent(setup not fully disclosed)
SWE-Bench Proresolved_rate	65.7%effort high · SWE-agent(setup not fully disclosed)
OfficeQA Proscore	66.2%effort high · Claude Code(setup not fully disclosed)
GDPval-AA v2elo	1678effort high(setup not fully disclosed)
OneMillionBench (with tools)score	65.4%effort high(setup not fully disclosed)
Humanity's Last Exam (with tools)accuracy	55.4%effort high(setup not fully disclosed)
GPQA Diamondaccuracy	92.3%effort high(setup not fully disclosed)
MCP Atlas Publicscore	83.7%effort high(setup not fully disclosed)
Toolathlon Verifiedpass_rate	74.1%effort high · 3 runs(setup not fully disclosed)