readable AI benchmarks (simplified)
Baidu
ERNIE 5.0 Thinking Preview
ERNIE 5.0 Thinking Preview has a Quality Score of 24.6, ranking 333rd among 571 scored models. It has a 128k token context window. Its Reliability Score is 27.2, ranking 361st among 573 scored models, below average (total average: 36.5).
Quality Score24.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability27.2
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 128k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 14.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -45.6
- Correct
- 22.1%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 89.9%
Correct 22.1%Incorrect 67.8%Partial / not attempted 10.1%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 13%
- GPQA Diamond
- 78%
- CritPt
- 1%
- AA-Omniscience
- 27%
Similar models
- ERNIE 4.5 300B A47BBaiduQuality Score 22.0Value Score not available
- Gemma 4 31B (Reasoning)GoogleQuality Score 24.3Value Score not available
- Nemotron 3 Super 120B A12B (Reasoning)NVIDIAQuality Score 24.5Value Score 20.1
- Nova 2.0 Pro Preview (Medium)AmazonQuality Score 23.6Value Score 15.8
- Mercury 2.5InceptionQuality Score 24.6Value Score 21.4
- Qwen3 VL 235B A22B (Reasoning)AlibabaQuality Score 23.7Value Score not available