readable AI benchmarks (simplified)
Tencent
Hy3-preview
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
- Hy3TencentQuality Score 43.3Value Score 43.2
- Hy3-previewTencentQuality Score 24.2Value Score 29.2
- MiMo-V2.5XiaomiQuality Score 37.5Value Score 37.8
- GPT-5.6 Luna (low)OpenAIQuality Score 40.0Value Score 36.9
- DeepSeek V4 Flash (high)DeepSeekQuality Score 41.3Value Score 42.0
- gpt-oss-120b (high)OpenAIQuality Score 22.1Value Score 24.0