Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Gemma 4 E4B (Non-reasoning) | AgMoDB

Gemma 4 E4B (Non-reasoning)

April 3, 2026Last synced Apr 7, 2026, 4:00 PM

Blended Price

Free/M

Input Price

Free/M

Output Price

Free/M

Speed

0 tok/s

TTFT

0.00s

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Gemma 4 E4B (Non-reasoning) 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

14.8

Coding Index

6.4

Math Index

—

MMLU Pro

— / 100

GPQA Diamond

0.5 / 100

HLE

0.0 / 100

LiveCodeBench

— / 100

SciCode

0.0 / 100

MATH-500

— / 100

AIME

— / 30

AIME 2025

— / 30

IFBench

0.4 / 100

LCR

0.2 / 100

Terminal-Bench Hard

0.1 / 100

τ²-Bench

0.3 / 100

Predicted

45.4 / 100

AA-Omniscience Hallucination RatePredicted

96.8 / 100

Aider PolyglotPredicted

46.4 / 100

AIMEPredicted

0.0 / 30

AIME 2025Predicted

0.3 / 30

AlpacaEval 2.0 LCPredicted

24.8 / 100

AlpacaEval 2.0 RawPredicted

19.6 / 100

ARC-AGI-1Predicted

45.9 / 100

ARC-AGI-1 Cost per TaskPredicted

0.2

ARC-AGI-2Predicted

2.6 / 100

ARC-AGI-2 Cost per TaskPredicted

0.4

BFCL (Berkeley Function Calling)Predicted

38.2

BigCodeBench CompletePredicted

40.8 / 100

BigCodeBench InstructPredicted

32.3 / 100

AA Intelligence Index (Matrix)Predicted

59.4

AA Long Context Reasoning (Matrix)Predicted

74.6

AIME 2024Predicted

82.9

AIME 2025 (Matrix)Predicted

94.5

Arena-Hard AutoPredicted

53.6

BrowseCompPredicted

76.3

BRUMO 2025Predicted

98.3

CMIMC 2025Predicted

88.8

CritPtPredicted

3.0

GPQA Diamond (Matrix)Predicted

71.1

GSM8KPredicted

88.9

HLE (Matrix)Predicted

27.4

HMMT Feb 2025Predicted

78.4

HMMT Nov 2025Predicted

92.4

HumanEvalPredicted

75.1

IFBench (Matrix)Predicted

46.5

IFEvalPredicted

84.8

IMO 2025Predicted

31.5

LiveCodeBench (Matrix)Predicted

60.1

MATH-500 (Matrix)Predicted

94.8

MathArena Apex 2025Predicted

4.7

MMLUPredicted

84.2

MMLU-Pro (Matrix)Predicted

75.1

MMMU-ProPredicted

79.1

MRCR v2Predicted

79.2

OSWorldPredicted

61.0

SimpleQAPredicted

43.4

SMT 2025Predicted

89.8

SWE-bench ProPredicted

47.7

Tau-Bench Telecom (Matrix)Predicted

98.1

Terminal-Bench 2.0Predicted

50.4

Terminal-Bench 1.0Predicted

29.0

USAMO 2025Predicted

13.5

Video-MMUPredicted

85.4

browsecompPredicted

76.5

BullshitBenchPredicted

32.1 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

3.1

Arc Agi 2Predicted

0.0

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.8

CAD-EvalPredicted

4.9

Chess PuzzlesPredicted

0.2

CyBenchPredicted

0.2

DeepResearchBenchPredicted

0.4

FictionLiveBenchPredicted

0.5

GdpvalPredicted

0.4

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

6.2

GSOPredicted

0.1

HellaSwagPredicted

0.1

HlePredicted

0.1

Lech Mazur WritingPredicted

7.6

METR Time HorizonsPredicted

5.2

OTIS Mock AIME 2024–2025Predicted

0.2

PIQAPredicted

0.8

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.4

The Agent CompanyPredicted

1.6

TriviaQAPredicted

8.7

VPCTPredicted

0.5

WinoGrandePredicted

0.8

FrontierMathPredicted

26.8 / 100

GAIA Level 1Predicted

38.1

GAIA Level 2Predicted

11.9

GAIA Level 3Predicted

0.4

GAIAPredicted

24.3 / 100

LegalBenchPredicted

63.0 / 100

LiveBench CodingPredicted

73.3 / 100

LiveBench Data AnalysisPredicted

59.2 / 100

LiveBench LanguagePredicted

70.9 / 100

LiveBench MathPredicted

78.1 / 100

LiveBench OverallPredicted

63.5 / 100

LiveBench ReasoningPredicted

64.9 / 100

LiveCodeBenchPredicted

0.3 / 100

LongBench v2 EasyPredicted

42.8

LongBench v2 HardPredicted

36.3

LongBench v2Predicted

33.2 / 100

MATH-500Predicted

0.7 / 100

MathVistaPredicted

60.4 / 100

MedQA (USMLE)Predicted

83.3

MLE-benchPredicted

46.2 / 100

MMLU ProPredicted

0.7 / 100

MMMUPredicted

70.2 / 100

MMTU Table UnderstandingPredicted

56.8 / 100

MT-BenchPredicted

7.8 / 10

NoLiMa (NIAH)Predicted

90.3 / 100

OCRBench v2Predicted

73.9 / 100

Open LLM AveragePredicted

21.3 / 100

Open LLM: BBHPredicted

48.8 / 100

Open LLM: GPQAPredicted

29.4 / 100

Open LLM: IFEvalPredicted

51.9 / 100

Open LLM: MATH Level 5Predicted

11.3 / 100

Open LLM: MMLU-PROPredicted

32.4 / 100

Open LLM: MUSRPredicted

40.0 / 100

RE-BenchPredicted

97.2

SimpleBenchPredicted

43.2 / 100

simpleqaPredicted

37.8

SWE-bench LitePredicted

23.7 / 100

SWE-bench VerifiedPredicted

57.5 / 100

tau-bench RetailPredicted

87.2 / 100

Vectara Factual ConsistencyPredicted

89.6 / 100

Vectara Hallucination RatePredicted

10.4 / 100

WebArenaPredicted

0.5 / 100

WeirdMLPredicted

36.1 / 100

WildBenchPredicted

38.5