- Score
- 5.8 (+0.12 points)
- Total Cost (Current Price)
- $0.055 · 91.1% cheaper
- Response Time (avg)
- 3.46s · 41.1% faster
Tencent
Release: 2026-11-04
Tested on: 2026-11-09 21:38
tencent/hy4::none
~770B total (~49B active)MoEClosedEstimated
Summary
Hy4 scores 5.7 on AI BENCHY and ranks #337. It has 10.0 reliability, a 40.6% pass rate, $0.114 total cost, and 5.87s average response time.
What makes Hy4 unique: It stands out most in Instructions following, where it ranks #1, while Tool Calling is its weakest area at #15.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 6.2 (+0.48 points)
- Total Cost (Current Price)
- $0.090 · 21.6% cheaper
- Response Time (avg)
- 3.60s · 38.6% faster
- Score
- 5.9 (+0.23 points)
- Total Cost (Current Price)
- $0.080 · 30.5% cheaper
- Response Time (avg)
- 3.95s · 32.8% 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.
5.7
Consistency
9.7
10.0
$0.114
Total Output Tokens
12,248
Total Input Tokens
235,746
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
1
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.
#337 Hy4
none- Cost
- $0.004
- Time
- 22.4s
- Tokens
- 2,679 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 | 3.1 | |
| Anti-AI Tricks | 3.6 | 10.0 | |
| Coding | 5.5 | 10.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 5.5 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |