AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Models

Phi-3 Mini Instruct 3.8B

April 23, 2024Last synced Nov 5, 2026, 12:19 AM

Blended Price

Free/M

Input Price

Free/M

Output Price

Free/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index
—
Coding Index
—
Math Index
—
MMLU Pro
43.5 / 100
GPQA Diamond
31.9 / 100
HLE
5.0 / 100
LiveCodeBench
11.6 / 100
SciCode
— / 100
MATH-500
45.7 / 100
AIME
4.0 / 30
AIME 2025
0.3 / 30
IFBench
23.9 / 100
LCR
— / 100
Terminal-Bench Hard
0.0 / 100
τ²-Bench
0.0 / 100

Performance Radar

Phi-3 Mini Instruct 3.8B
Field Average

Hidden, no data: AgMoBench Agentic, AgMoBench Robustness, Output Speed

External Benchmarks

AA-Omniscience AccuracyPredicted
45.0 / 100
AA-Omniscience Hallucination RatePredicted
95.2 / 100
Aider PolyglotPredicted
10.5 / 100
AlpacaEval 2.0 LCPredicted
28.0 / 100
AlpacaEval 2.0 RawPredicted
22.2 / 100
ARC-AGI-1Predicted
7.4 / 100
ARC-AGI-1 Cost per TaskPredicted
0.0
ARC-AGI-2Predicted
0.0 / 100
ARC-AGI-2 Cost per TaskPredicted
0.0
BFCL (Berkeley Function Calling)Predicted
24.0
BigCodeBench CompletePredicted
40.6 / 100
BigCodeBench InstructPredicted
32.4 / 100
AA Intelligence Index (Matrix)Predicted
58.2
AA Long Context Reasoning (Matrix)Predicted
72.7
AIME 2024Predicted
20.4
AIME 2025 (Matrix)Predicted
25.9
Arena-Hard AutoPredicted
24.1
BrowseCompPredicted
73.9
BRUMO 2025Predicted
93.9
CMIMC 2025Predicted
80.5
CritPtPredicted
0.6
GPQA Diamond (Matrix)Predicted
39.3
GSM8KPredicted
73.4
HLE (Matrix)Predicted
15.8
HMMT Feb 2025Predicted
36.8
HMMT Nov 2025Predicted
91.1
HumanEvalPredicted
67.7
IFBench (Matrix)Predicted
27.3
IFEvalPredicted
73.2
IMO 2025Predicted
18.1
LiveCodeBench (Matrix)Predicted
29.0
MATH-500 (Matrix)Predicted
84.0
MathArena Apex 2025Predicted
2.7
MMLUPredicted
64.0
MMLU-Pro (Matrix)Predicted
41.8
MMMU-ProPredicted
77.6
MRCR v2Predicted
77.0
OSWorld (Unversioned Matrix Import)Predicted
37.7 / 100
SimpleQAPredicted
26.0
SMT 2025Predicted
83.8
SWE-bench ProPredicted
28.4
Tau-Bench Telecom (Matrix)Predicted
97.3
Terminal-Bench 2.0Predicted
38.0
Terminal-Bench 1.0Predicted
16.0
USAMO 2025Predicted
5.1
Video-MMUPredicted
84.9
browsecompPredicted
74.4
BullshitBenchPredicted
19.2 / 100
Aider PolyglotPredicted
0.0
Apex AgentsPredicted
3.0
Arc Agi 2Predicted
0.0
BALROGPredicted
0.0
BIG-Bench HardPredicted
3.0
BoolQPredicted
0.9
CAD-EvalPredicted
9.1
Chess PuzzlesPredicted
0.2
CyBenchPredicted
0.1
DeepResearchBenchPredicted
0.3
FictionLiveBenchPredicted
0.3
GdpvalPredicted
0.3
GeoBenchPredicted
0.0
GSM8K (Epoch)Predicted
5.0
GSOPredicted
0.0
HellaSwagPredicted
3.6
HlePredicted
0.0
Lech Mazur WritingPredicted
6.7
METR Time HorizonsPredicted
0.7
OTIS Mock AIME 2024–2025Predicted
0.0
PIQAPredicted
1.0
PosttrainbenchPredicted
0.0
SimpleQA Verified (Epoch)Predicted
0.3
The Agent CompanyPredicted
0.8
TriviaQAPredicted
3.6
VPCTPredicted
0.4
WinoGrandePredicted
0.7
FrontierMathPredicted
20.0 / 100
GAIA Level 1Predicted
9.0
GAIA Level 2Predicted
1.2
GAIA Level 3Predicted
0.0
GAIAPredicted
5.4 / 100
LegalBenchPredicted
51.4 / 100
LiveBench CodingPredicted
69.6 / 100
LiveBench Data AnalysisPredicted
49.9 / 100
LiveBench LanguagePredicted
61.3 / 100
LiveBench MathPredicted
69.6 / 100
LiveBench OverallPredicted
53.1 / 100
LiveBench ReasoningPredicted
49.5 / 100
LongBench v2 EasyPredicted
31.5
LongBench v2 HardPredicted
29.5
LongBench v2Predicted
27.1 / 100
MathVistaPredicted
20.0 / 100
MedQA (USMLE)Predicted
55.1
MLE-bench (Original)Predicted
27.1 / 100
MMMUPredicted
52.3 / 100
MMTU Table UnderstandingPredicted
44.1 / 100
MT-BenchPredicted
7.8 / 10
NoLiMa (NIAH)Predicted
86.2 / 100
OCRBench v2Predicted
64.9 / 100
Open LLM AveragePredicted
33.0 / 100
Open LLM: BBHPredicted
58.1 / 100
Open LLM: GPQAPredicted
31.8 / 100
Open LLM: IFEvalPredicted
74.1 / 100
Open LLM: MATH Level 5Predicted
27.6 / 100
Open LLM: MMLU-PROPredicted
42.0 / 100
Open LLM: MUSRPredicted
41.4 / 100
RE-BenchPredicted
21.1
SimpleBenchPredicted
23.3 / 100
simpleqaPredicted
21.1
SWE-bench LitePredicted
6.9 / 100
SWE-bench VerifiedPredicted
29.6 / 100
tau-bench RetailPredicted
83.5 / 100
Vectara Factual ConsistencyPredicted
92.2 / 100
Vectara Hallucination RatePredicted
7.8 / 100
WebArenaPredicted
0.8 / 100
WeirdMLPredicted
13.7 / 100
WildBenchPredicted
39.5

How Phi-3 Mini Instruct 3.8B Compares

Axes

Filters

$0.00 – $67.5
≥ 1.4

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu
openai
zai
meta
nvidia
xai
upstage
deepseek
alibaba
mistral
nous-research
aws
google
anthropic
xiaomi
stepfun
kimi
reflection
minimax
azure
inclusionai
reka-ai
cohere
bytedance_seed
inception
tencent
thinking-machines
Bubble size = Context Window
8191.00
2000000.00
Compare with other models