- Score
- 8.9 (+3.06 points)
- Total Cost (Current Price)
- $0.047 · 98.5% cheaper
- Response Time (avg)
- 5.30s · 97.6% faster
Tencent
Release: 2026-11-04
Tested on: 2026-11-10 00:46
tencent/hy4::high
~770B total (~49B active)MoEClosedEstimated
Summary
Hy4 scores 5.8 on AI BENCHY and ranks #327. It has 9.7 reliability, a 56.5% pass rate, $3.055 total cost, and 219.63s average response time.
What makes Hy4 unique: It stands out most in Coding, where it ranks #1, while Data parsing and extraction is its weakest area at #16. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 8.6 (+2.79 points)
- Total Cost (Current Price)
- $0.184 · 94.0% cheaper
- Response Time (avg)
- 4.08s · 98.1% faster
- Score
- 9.4 (+3.55 points)
- Total Cost (Current Price)
- $0.183 · 94.0% cheaper
- Response Time (avg)
- 6.24s · 97.2% faster
Model facts
Researched on 2026-11-09
- Parameters
- ~770B total (~49B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. On the research date no official Hy4 (non-preview) weights or license are public; the expected tencent/Hy4 Hugging Face repository is not accessible. Counts are estimates carried from the Apache-2.0 Hy4 Preview backbone (770B total / 49B active MoE). Reclassify when Tencent publishes the exact checkpoint.
5.8
Consistency
8.2
9.7
$3.055
Total Output Tokens
2,328,895
Total Input Tokens
341,340
Input Price
$0.417 / 1M
Output Price
$1.251 / 1M
Cache Read Price
$0.021 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#327 Hy4
high- Cost
- $0.030
- Time
- 162.4s
- Tokens
- 23,596 tok
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 4.7 | 1.6 | |
| Anti-AI Tricks | 8.7 | 7.9 | |
| Coding | 7.5 | 10.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 6.1 | 5.6 | |
| Domain specific | 3.0 | 10.0 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 7.3 | 5.8 | |
| Puzzle Solving | 7.7 | 10.0 | |
| Tool Calling | 4.6 | 1.8 | |
| Trivia | 3.0 | 10.0 |