Advertise here
#341

Hy4 preview

Tencent Release: 2026-08-29 Tested on: 2026-10-01 04:18 tencent/hy4-preview::none
770B total (49B active)MoEOpen source
(low) (none)

Summary

Hy4 preview scores 4.9 on AI BENCHY and ranks #341. It has 6.2 reliability, a 15.9% pass rate, $0.165 total cost, and 40.38s average response time.

What makes Hy4 preview unique: It stands out most in Domain specific, where it ranks #1, while Tool Calling is its weakest area at #10.

Model facts

Researched on 2026-08-29

Reported
Parameters
770B total (49B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

Vendor-reported backbone counts exclude the native 10B total / 0.7B active MTP layer used for speculative decoding.

Parameter source 1 Parameter source 2 Availability source

Score

4.9

Consistency

9.4

Reliability

6.2

Total Cost (Current Price)

$0.165

Total Output Tokens

9,430

Total Input Tokens

185,167

Input Price

$0.751 / 1M

Output Price

$2.251 / 1M

Cache Read Price

$0.038 / 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.

Tests Correct

Wrong Tests: 20

Attempt pass rate: 15.9%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

40.38s

Response Time (max): 95.32s

Response Time (total): 928.76s

Wrong answer: 14 API error: 2 Did not follow instructions: 2 Extra formatting: 1 Invalid tool call: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#341 Hy4 preview

none
This operation was aborted
Cost
$0.000
Time
0.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 04:18 Re-test 4.9 6.2 $0.165 Current run
2026-08-29 14:22 Initial run 4.1 1.3 $0.035 Compare

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 04:18 · Current run69/69 attempts4.99.46.23/2319,430185,167$0.16540.38s
2026-08-29 14:22 · Initial run66/66 attempts4.17.81.33/2266,15423,473$0.03551.97s
Difference—+0.7+1.6+4.90-5+3276+161694+$0.130-11586ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-10-06 16:43 $0.751 / 1M $2.251 / 1M $0.038 / 1M N/A

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Hy4 previewnonevsQwen3.5-9BnoneHy4 previewnonevsGLM 4.7 FlashnoneHy4 previewnonevsMiMo-V2.5noneHy4 previewnonevsMercury 2.5 PreviewdefaultHy4 previewnonevsLing 2.6 1tdefaultHy4 previewnonevsNemotron 3.5 LightningmediumFree AvailableHy4 previewnonevsLaguna S 2.1highFree AvailableHy4 previewnonevsNorth Mini CodedefaultFree AvailableHy4 previewnonevsQwen3 Coder NextdefaultHy4 previewnonevsLaguna S 2.1noneFree Available

Category Breakdown

Category Score Consistency Tests Correct
Agentic 5.0 10.0
Anti-AI Tricks 3.3 9.6
Coding 3.8 9.4
Combined 3.0 10.0
Data parsing and extraction 8.7 10.0
Domain specific 6.8 10.0
General Intelligence 5.1 10.0
Instructions following 7.0 8.9
Puzzle Solving 4.6 7.0
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models