Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Meta: Llama 3.2 3B Instruct (free) | AgMoDB

Meta: Llama 3.2 3B Instruct (free)

Last synced Apr 7, 2026, 2:04 PM131K context

Blended Price

Free/M

Input Price

Free/M

Output Price

Free/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Meta: Llama 3.2 3B Instruct (free) Compares

Axes

X Axis

Y Axis

Bubble Size

Filters

Blended Price (USD)$0.00 – $30.0

AgMoBench Overall≥ 3.5

Providers

ai21-labsalibabaanthropicawsazurebaiducoheredeepseek

Show quadrants

anthropic

openai

google

meta

mistral

nvidia

kimi

xai

azure

deepseek

aws

cohere

baidu

ai21-labs

zai

reka-ai

xiaomi

alibaba

minimax

ibm

Bubble size = Context Window

16384.00

2000000.00

Compare with other models

—

Coding Index

—

Math Index

—

MMLU Pro

— / 100

GPQA Diamond

— / 100

HLE

— / 100

LiveCodeBench

— / 100

SciCode

— / 100

MATH-500

— / 100

AIME

— / 30

AIME 2025

— / 30

IFBench

— / 100

LCR

— / 100

Terminal-Bench Hard

— / 100

τ²-Bench

— / 100

Predicted

49.6 / 100

AA-Omniscience Hallucination RatePredicted

96.4 / 100

Aider PolyglotPredicted

10.0 / 100

AIMEPredicted

0.0 / 30

AIME 2025Predicted

0.0 / 30

AlpacaEval 2.0 LCPredicted

19.6 / 100

AlpacaEval 2.0 RawPredicted

15.8 / 100

ARC-AGI-1Predicted

17.4 / 100

ARC-AGI-1 Cost per TaskPredicted

0.1

ARC-AGI-2Predicted

0.6 / 100

ARC-AGI-2 Cost per TaskPredicted

0.1

AA Intelligence Index (Matrix)Predicted

51.6

AA Long Context Reasoning (Matrix)Predicted

90.2

AIME 2024Predicted

15.7

AIME 2025 (Matrix)Predicted

52.6

Arena-Hard AutoPredicted

11.6

BrowseCompPredicted

85.3

BRUMO 2025Predicted

99.2

CMIMC 2025Predicted

94.4

CritPtPredicted

5.1

GPQA Diamond (Matrix)Predicted

35.8

GSM8KPredicted

83.3

HLE (Matrix)Predicted

23.8

HMMT Feb 2025Predicted

53.3

HMMT Nov 2025Predicted

93.5

HumanEvalPredicted

64.0

IFBench (Matrix)Predicted

17.1

IFEvalPredicted

71.0

IMO 2025Predicted

34.4

LiveCodeBench (Matrix)Predicted

25.2

MATH-500 (Matrix)Predicted

79.9

MathArena Apex 2025Predicted

11.5

MMLUPredicted

69.5

MMLU-Pro (Matrix)Predicted

51.5

MMMU-ProPredicted

78.5

MRCR v2Predicted

92.0

OSWorldPredicted

30.8

SimpleQAPredicted

31.3

SMT 2025Predicted

76.4

SWE-bench ProPredicted

81.8

Tau-Bench Telecom (Matrix)Predicted

98.7

Terminal-Bench 2.0Predicted

67.1

Terminal-Bench 1.0Predicted

23.7

USAMO 2025Predicted

7.1

Video-MMUPredicted

83.8

browsecompPredicted

87.1

BullshitBenchPredicted

27.9 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

4.1

Arc Agi 2Predicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.9

CAD-EvalPredicted

4.0

Chess PuzzlesPredicted

0.3

CyBenchPredicted

0.1

DeepResearchBenchPredicted

0.4

FictionLiveBenchPredicted

0.4

GdpvalPredicted

0.5

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

0.0

GSOPredicted

0.2

HellaSwagPredicted

0.1

HlePredicted

0.2

Lech Mazur WritingPredicted

6.7

METR Time HorizonsPredicted

3.6

OTIS Mock AIME 2024–2025Predicted

0.0

PIQAPredicted

0.8

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.5

The Agent CompanyPredicted

0.7

TriviaQAPredicted

7.7

VPCTPredicted

0.2

WinoGrandePredicted

0.7

FrontierMathPredicted

42.5 / 100

GAIA Level 1Predicted

6.5

GAIA Level 2Predicted

2.8

GAIA Level 3Predicted

0.0

GAIAPredicted

3.9 / 100

GPQA DiamondPredicted

0.2 / 100

HLEPredicted

0.0 / 100

IFBenchPredicted

0.2 / 100

LCRPredicted

0.0 / 100

LegalBenchPredicted

23.0 / 100

LiveBench CodingPredicted

75.9 / 100

LiveBench Data AnalysisPredicted

64.1 / 100

LiveBench LanguagePredicted

76.0 / 100

LiveBench MathPredicted

82.8 / 100

LiveBench OverallPredicted

68.2 / 100

LiveBench ReasoningPredicted

70.7 / 100

LiveCodeBenchPredicted

0.0 / 100

LongBench v2 EasyPredicted

25.6

LongBench v2 HardPredicted

22.2

LongBench v2Predicted

25.2 / 100

MATH-500Predicted

0.2 / 100

MathVistaPredicted

43.1 / 100

MLE-benchPredicted

36.8 / 100

MMLU ProPredicted

0.3 / 100

MMMUPredicted

48.5 / 100

MMTU Table UnderstandingPredicted

52.4 / 100

MT-BenchPredicted

6.7 / 10

NoLiMa (NIAH)Predicted

79.9 / 100

OCRBench v2Predicted

56.9 / 100

RE-BenchPredicted

99.1

SciCodePredicted

0.0 / 100

SimpleBenchPredicted

29.9 / 100

simpleqaPredicted

26.7

SWE-bench LitePredicted

5.6 / 100

SWE-bench VerifiedPredicted

32.2 / 100

τ²-BenchPredicted

0.0 / 100

tau-bench RetailPredicted

90.2 / 100

Terminal-Bench HardPredicted

0.0 / 100

Vectara Factual ConsistencyPredicted

93.7 / 100

Vectara Hallucination RatePredicted

6.3 / 100

WebArenaPredicted

0.0 / 100

WeirdMLPredicted

13.5 / 100

WildBenchPredicted

29.4

BFCL (Berkeley Function Calling)bfcl

21.9

BigCodeBench Completebigcodebench

28.3 / 100

BigCodeBench Instructbigcodebench

23.4 / 100

BALROGepoch_ai

0.0

HuggingFace Downloads (30d)hf-downloads

1247282.0

HuggingFace Likeshf-downloads

707.0

Open LLM Averageopen_llm_leaderboard

24.2 / 100

Open LLM: BBHopen_llm_leaderboard

46.1 / 100

Open LLM: GPQAopen_llm_leaderboard

27.9 / 100

Open LLM: IFEvalopen_llm_leaderboard

73.9 / 100

Open LLM: MATH Level 5open_llm_leaderboard

17.7 / 100

Open LLM: MMLU-PROopen_llm_leaderboard

31.9 / 100

Open LLM: MUSRopen_llm_leaderboard

35.3 / 100