readable AI benchmarks (simplified)
Tencent
Hy3-preview (Non-reasoning)
Hy3-preview (Non-reasoning) has a Quality Score of 29.4, ranking 209th among 398 scored models. Per 1M tokens, pricing is $0.063 input, $0.210 output, and $0.021 cached input. It has a 256k token context window. Its Reliability Score is 32.5, ranking 226th among 399 scored models, below average (total average: 37.9). Its Value Score is 27.6, low compared with the total Value average of 33.2.
Quality Score29.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score27.6
Factual reliability32.5
Cache Discount67%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.063
- Output
- $0.210
- Cached Input
- $0.021
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 17.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -35.0
- Correct
- 23.2%
- Blended price
- $0.048
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 81.3%
Correct 23.2%Incorrect 58.1%Partial / not attempted 18.7%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 7%
- GPQA Diamond
- 73%
- CritPt
- 0%
- AA-Omniscience
- 33%
- AA-LCR
- 42%
Similar models
- Hy3TencentQuality Score 39.8Value Score 35.6
- Hy3-previewTencentQuality Score not availableValue Score not available
- MiMo-V2.5-Pro (Non-reasoning)XiaomiQuality Score 29.6Value Score 25.3
- DeepSeek V4 Flash 0420 (Non-reasoning)DeepSeekQuality Score 28.5Value Score 26.7
- GPT-5.6 Luna (Non-reasoning)OpenAIQuality Score 30.7Value Score 26.2
- Qwen3.5 27B (Non-reasoning)AlibabaQuality Score 28.0Value Score not available