Phi-3 Mini Instruct 3.8B
MicrosoftPhi
Release Date
2024-04-23
Parameters
—
Context Length
16K
Modalities
text
Capability Radar
16
general
11
coding
11
reasoning
18
scienceest.
11
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 472 | 5.0 | AA |
| General Ranking | 483 | 15.0 | AA |
| Math Reasoning | 338 | 9.0 | AA |
| Reasoning | 27 | 83.0 | LS |
| Science | 466 | 16.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
56.1%SR
Code
HumanEval
82.6%SR
Creativity
Arena Hard
75.4%SR
Factuality
SimpleQA
3.0%SR
Finance
MMLU
84.8%SR
MMLU-Pro
70.4%SR
General
IFEval
63.0%SR
PhiBench
56.2%SR
LiveBench
47.6%SR
Math
MGSM
80.6%SR
MATH
80.4%SR
DROP
75.5%SR
Reasoning
HumanEval+
82.8%SR
AA Evaluation Indices
Intelligence Index4.6
Math 5000.5
Mmlu Pro0.4
Gpqa0.3
Math Index0.3
Ifbench0.2
Livecodebench0.1
Scicode0.1
Hle0.0
Aime0.0
Lcr0.0
Aime 250.0
Terminalbench Hard0.0
Tau20.0
LLM Stats Category Scores
Language80
Legal80
Finance80
Healthcare80
Code80
Creativity80
Writing80
Math70
Reasoning70
Instruction Following60
Physics60
Structured Output60
General60
Biology60
Chemistry60
Factuality0
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
4 providers
Cheapest: Kilo GatewayMost Expensive: Azure
ProviderInputOutput
1Kilo GatewayCheapest
$0.06
$0.14
2OpenRouter
$0.065
$0.14
3Azure Cognitive Services
$0.13
$0.52
4Azure
$0.13
$0.52
Compare pricing across different API providers for this model.