readable AI benchmarks (simplified)

readable AI benchmarks

Tencent

Hy3-preview

reasoning · open weights · Apr 23, 2026

Hy3-preview has a Quality Score of 30.2, ranking 50th among 53 scored models. Per 1M tokens, pricing is $0.065 input, $0.235 output, and $0.025 cached input. Its Reliability Score is 32.7, ranking 50th among 53 scored models, below average (total average: 50.1). Its Value Score is 37.1, around average compared with the total Value average of 39.6.

Quality Score30.2coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score37.1
Reliability32.7
Cache Discount61%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
not available
Weights
open weights

Token prices USD per 1M tokens

Input
$0.065
Output
$0.235
Cached Input
$0.025
Cache write
not available
Cost per task
not available

Capability

Intelligence
33.6
Coding
not available
Agentic
not available
Omniscience
-34.6
Correct
28.0%
Blended price
$0.054

Answer outcomes

Attempt rate: 90.6%

Correct 28.0%Incorrect 62.6%Abstained 9.4%

Artificial Analysis benchmarks

SciCode
41%
Humanity’s Last Exam
26%
GPQA Diamond
87%
CritPt
5%
AA-Omniscience
33%
AA-LCR
55%

Similar models