HY3
tencent
Single-source measurements
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps. Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Capabilities & Recommended Uses
Strengths
- •Tencent's latest reasoning-focused model
- •Strong bilingual Chinese-English coding support
- •Competitive performance for its price tier
- •Growing ecosystem in Chinese tech
Best For
- •Bilingual development (CN/EN)
- •Budget reasoning tasks
- •Code generation and debugging
- •Chinese tech ecosystem
Weaknesses
- •Less competitive on hard coding benchmarks
- •Smaller international community presence
Benchmark evidence and ranking method · HY3
Single-source measurements
Test configuration: unspecified
Terminal-Bench 2.1: 64.42% · SciCode: 48.61%
ModelRank assigns editorial tiers using public coding evidence, not automatic index thresholds or statistically proven classes. Price, speed, context size and sponsorship do not affect tiers.
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps.
Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Data checked: 2026-09-10. Snapshot date is the retrieval date, not necessarily the evaluation date.
Compare with Alternatives
Frequently Asked Questions
What is HY3's coding score and ranking tier?
HY3 by tencent is rated as Tier B on ModelRank with a coding score of 88.93 (Reference baseline = 100) as a reference index derived from public benchmark evidence. Tiers are editorial assessments; the index does not establish real-world capability differences.
What is the API pricing and context window for HY3?
HY3 features a 262,144 token context window. Pricing is $0.132 per 1M input tokens and $0.528 per 1M output tokens (OpenRouter quote).
What programming tasks is HY3 best suited for?
HY3 is recommended for: Bilingual development (CN/EN), Budget reasoning tasks, Code generation and debugging, Chinese tech ecosystem. Key strengths include: Tencent's latest reasoning-focused model, Strong bilingual Chinese-English coding support, Competitive performance for its price tier, Growing ecosystem in Chinese tech.
Try HY3
Last updated: September 7, 2026