readable AI benchmarks (simplified)
Alibaba
Qwen3 VL 4B (Reasoning)
Qwen3 VL 4B (Reasoning) has a Quality Score of 11.4, ranking 228th among 238 scored models. It has a 256k token context window. Its Reliability Score is 15.8, ranking 236th among 245 scored models, below average (total average: 46.4).
Quality Score11.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability15.8
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 256k tokens
- Weights
- open 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
- 7.0
- Omniscience (native net)
- -68.4
- Correct
- 12.2%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 92.8%
Correct 12.2%Incorrect 80.6%Partial / not attempted 7.2%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 49%
- CritPt
- 0%
- AA-LCR
- 21%
Similar models
- Qwen3 8B (Reasoning)AlibabaQuality Score 11.4Value Score not available
- Qwen3 1.7B (Reasoning)AlibabaQuality Score 8.2Value Score not available
- Qwen3 32B (Reasoning)AlibabaQuality Score 16.0Value Score not available
- Qwen3 30B A3B (Reasoning)AlibabaQuality Score 15.9Value Score not available
- Qwen3 14B (Reasoning)AlibabaQuality Score 16.0Value Score not available
- Qwen3 0.6B (Reasoning)AlibabaQuality Score 7.7Value Score not available