readable AI benchmarks (simplified)
Alibaba
Qwen3 4B 2507 Instruct
Qwen3 4B 2507 Instruct has a Quality Score of 14.7, ranking 486th among 551 scored models. It has a 262,144 token context window. Its Reliability Score is 19.0, ranking 470th among 553 scored models, below average (total average: 35.6).
Quality Score14.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability19.0
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 262,144 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
- 6.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- -61.9
- Correct
- 10.9%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 83.7%
Correct 10.9%Incorrect 72.8%Partial / not attempted 16.3%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 52%
- CritPt
- 0%
- AA-Omniscience
- 19%
- AA-LCR
- 11%
Similar models
- Qwen3 30B A3B 2507 InstructAlibabaQuality Score 14.2Value Score not available
- Qwen3 30B A3B (Non-reasoning)AlibabaQuality Score 13.6Value Score not available
- Qwen3 14B (Non-reasoning)AlibabaQuality Score 13.5Value Score not available
- Qwen3 VL 30B A3B InstructAlibabaQuality Score 15.2Value Score not available
- Qwen3 VL 32B InstructAlibabaQuality Score 15.6Value Score not available
- Qwen3.5 4B (Non-reasoning)AlibabaQuality Score 14.6Value Score not available