readable AI benchmarks

Microsoft

Phi-4 Mini Instruct

non-reasoning · open weights · Feb 26, 2024

Quality Score6.4
Value Score8.2
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
Cached Output
not available
Cost per task
not available

Capability

Intelligence
5.7
Coding
3.8
Agentic
not available
Omniscience
-61.1
Correct
9.5%
Blended price
$0.0000

Answer outcomes

Correct 9.5%Incorrect 70.6%Abstained 19.9%

Artificial Analysis benchmarks

GDPval-AA v2
0%
Terminal-Bench v2.1
0%
SciCode
11%
Humanity’s Last Exam
4%
GPQA Diamond
33%
CritPt
0%
AA-Omniscience
19%
AA-LCR
17%

Similar models