readable AI benchmarks (simplified)
Microsoft
Phi-4 Mini Instruct
Phi-4 Mini Instruct has a Quality Score of 14.6, ranking 509th among 571 scored models. Per 1M tokens, pricing is $0.0000 input and $0.0000 output. It accepts text input, outputs text, and has a 128k token context window. Its Reliability Score is 19.5, ranking 483rd among 573 scored models, below average (total average: 36.5).
Quality Score14.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability19.5
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.0000
- Output
- $0.0000
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 6.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -61.1
- Correct
- 9.5%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 80.1%
Correct 9.5%Incorrect 70.6%Partial / not attempted 19.9%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 33%
- CritPt
- 0%
- AA-Omniscience
- 19%
- AA-LCR
- 15%
Similar models
- Phi-4MicrosoftQuality Score 15.6Value Score not available
- Phi-3 Mini Instruct 3.8BMicrosoftQuality Score not availableValue Score not available
- Phi-4 Multimodal InstructMicrosoftQuality Score not availableValue Score not available
- Qwen3 4B 2507 InstructAlibabaQuality Score 14.7Value Score not available
- Granite 4.0 H SmallIBMQuality Score 14.4Value Score not available
- EXAONE 4.0 32B (Non-reasoning)LG AI ResearchQuality Score 14.2Value Score not available