Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Google: Gemma 3 12B (free) | AgMoDB

Google: Gemma 3 12B (free)

Last synced Apr 7, 2026, 2:04 PM33K 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 Google: Gemma 3 12B (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

37.3 / 100

AA-Omniscience Hallucination RatePredicted

93.8 / 100

Aider PolyglotPredicted

27.4 / 100

AIMEPredicted

0.8 / 30

AIME 2025Predicted

0.4 / 30

AlpacaEval 2.0 LCPredicted

45.2 / 100

AlpacaEval 2.0 RawPredicted

35.5 / 100

ARC-AGI-1Predicted

1.3 / 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

41.6

BigCodeBench CompletePredicted

65.3 / 100

BigCodeBench InstructPredicted

55.1 / 100

AA Intelligence Index (Matrix)Predicted

71.2

AA Long Context Reasoning (Matrix)Predicted

68.0

AIME 2024Predicted

65.1

AIME 2025 (Matrix)Predicted

26.9

Arena-Hard AutoPredicted

75.0

BrowseCompPredicted

45.8

BRUMO 2025Predicted

45.7

CMIMC 2025Predicted

53.7

CritPtPredicted

0.0

GPQA Diamond (Matrix)Predicted

63.6

GSM8KPredicted

90.9

HLE (Matrix)Predicted

8.3

HMMT Feb 2025Predicted

31.5

HMMT Nov 2025Predicted

85.9

HumanEvalPredicted

85.3

IFBench (Matrix)Predicted

31.8

IFEvalPredicted

83.7

IMO 2025Predicted

6.5

LiveCodeBench (Matrix)Predicted

54.1

MATH-500 (Matrix)Predicted

94.5

MathArena Apex 2025Predicted

0.2

MMLUPredicted

83.7

MMLU-Pro (Matrix)Predicted

73.1

MMMU-ProPredicted

81.8

MRCR v2Predicted

71.6

OSWorldPredicted

27.6

SimpleQAPredicted

15.0

SMT 2025Predicted

68.1

SWE-bench ProPredicted

29.5

Tau-Bench Telecom (Matrix)Predicted

92.1

Terminal-Bench 2.0Predicted

8.6

Terminal-Bench 1.0Predicted

10.6

USAMO 2025Predicted

4.7

Video-MMUPredicted

86.9

browsecompPredicted

40.4

BullshitBenchPredicted

7.6 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

1.7

Arc Agi 2Predicted

0.0

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.9

CAD-EvalPredicted

5.7

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.1

DeepResearchBenchPredicted

0.3

FictionLiveBenchPredicted

0.3

GdpvalPredicted

0.1

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

68.9

GSOPredicted

0.0

HellaSwagPredicted

58.3

HlePredicted

0.0

Lech Mazur WritingPredicted

7.1

METR Time HorizonsPredicted

0.1

OTIS Mock AIME 2024–2025Predicted

0.2

PIQAPredicted

0.9

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.2

The Agent CompanyPredicted

1.6

TriviaQAPredicted

1.9

VPCTPredicted

0.3

WinoGrandePredicted

0.9

FrontierMathPredicted

6.9 / 100

GAIA Level 1Predicted

52.4

GAIA Level 2Predicted

37.4

GAIA Level 3Predicted

4.4

GAIAPredicted

36.6 / 100

GPQA DiamondPredicted

0.6 / 100

HLEPredicted

0.0 / 100

IFBenchPredicted

0.4 / 100

LCRPredicted

0.0 / 100

LegalBenchPredicted

92.9 / 100

LiveBench CodingPredicted

59.1 / 100

LiveBench Data AnalysisPredicted

30.4 / 100

LiveBench LanguagePredicted

37.1 / 100

LiveBench MathPredicted

44.6 / 100

LiveBench OverallPredicted

31.8 / 100

LiveBench ReasoningPredicted

22.5 / 100

LiveCodeBenchPredicted

0.5 / 100

LongBench v2 EasyPredicted

48.8

LongBench v2 HardPredicted

47.3

LongBench v2Predicted

42.6 / 100

MATH-500Predicted

0.9 / 100

MathVistaPredicted

59.2 / 100

MedQA (USMLE)Predicted

81.5

MLE-benchPredicted

9.4 / 100

MMLU ProPredicted

0.8 / 100

MMMUPredicted

68.6 / 100

MMTU Table UnderstandingPredicted

50.1 / 100

MT-BenchPredicted

8.0 / 10

NoLiMa (NIAH)Predicted

94.4 / 100

OCRBench v2Predicted

85.4 / 100

Open LLM AveragePredicted

47.8 / 100

Open LLM: BBHPredicted

72.1 / 100

Open LLM: GPQAPredicted

37.0 / 100

Open LLM: IFEvalPredicted

75.1 / 100

Open LLM: MATH Level 5Predicted

54.5 / 100

Open LLM: MMLU-PROPredicted

59.3 / 100

Open LLM: MUSRPredicted

46.8 / 100

RE-BenchPredicted

0.0

SciCodePredicted

0.5 / 100

SimpleBenchPredicted

17.7 / 100

simpleqaPredicted

16.5

SWE-bench LitePredicted

18.6 / 100

SWE-bench VerifiedPredicted

33.2 / 100

τ²-BenchPredicted

0.1 / 100

tau-bench RetailPredicted

66.8 / 100

Terminal-Bench HardPredicted

0.1 / 100

WebArenaPredicted

23.5 / 100

WeirdMLPredicted

24.5 / 100

WildBenchPredicted

48.9

Vectara Factual Consistencyvectara_hallucination

95.6 / 100

Vectara Hallucination Ratevectara_hallucination

4.4 / 100