Models Agents EvalsIndustry

AgMoDB by @mistakeknot

LFM2 2.6B | AgMoDB

LFM2 2.6B

September 23, 2025Last 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 LFM2 2.6B 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

8.0

Coding Index

1.4

Math Index

8.3

MMLU Pro

0.3 / 100

GPQA Diamond

0.3 / 100

HLE

0.1 / 100

LiveCodeBench

0.1 / 100

SciCode

0.0 / 100

MATH-500

— / 100

AIME

— / 30

AIME 2025

0.1 / 30

IFBench

0.2 / 100

LCR

0.0 / 100

Terminal-Bench Hard

0.0 / 100

τ²-Bench

0.1 / 100

Predicted

48.9 / 100

AA-Omniscience Hallucination RatePredicted

96.8 / 100

Aider PolyglotPredicted

22.5 / 100

AIMEPredicted

0.0 / 30

AlpacaEval 2.0 LCPredicted

19.9 / 100

AlpacaEval 2.0 RawPredicted

15.9 / 100

ARC-AGI-1Predicted

49.0 / 100

ARC-AGI-1 Cost per TaskPredicted

0.3

ARC-AGI-2Predicted

3.1 / 100

ARC-AGI-2 Cost per TaskPredicted

0.4

BFCL (Berkeley Function Calling)Predicted

26.2

BigCodeBench CompletePredicted

30.4 / 100

BigCodeBench InstructPredicted

23.9 / 100

AA Intelligence Index (Matrix)Predicted

52.7

AA Long Context Reasoning (Matrix)Predicted

76.0

AIME 2024Predicted

45.0

AIME 2025 (Matrix)Predicted

84.7

Arena-Hard AutoPredicted

22.6

BrowseCompPredicted

84.2

BRUMO 2025Predicted

99.3

CMIMC 2025Predicted

92.1

CritPtPredicted

6.5

GPQA Diamond (Matrix)Predicted

51.8

GSM8KPredicted

76.8

HLE (Matrix)Predicted

30.0

HMMT Feb 2025Predicted

70.5

HMMT Nov 2025Predicted

93.6

HumanEvalPredicted

61.5

IFBench (Matrix)Predicted

38.3

IFEvalPredicted

77.5

IMO 2025Predicted

38.3

LiveCodeBench (Matrix)Predicted

39.2

MATH-500 (Matrix)Predicted

88.3

MathArena Apex 2025Predicted

11.2

MMLUPredicted

76.9

MMLU-Pro (Matrix)Predicted

61.8

MMMU-ProPredicted

76.6

MRCR v2Predicted

80.6

OSWorldPredicted

74.2

SimpleQAPredicted

45.4

SMT 2025Predicted

91.8

SWE-bench ProPredicted

54.0

Tau-Bench Telecom (Matrix)Predicted

98.7

Terminal-Bench 2.0Predicted

67.0

Terminal-Bench 1.0Predicted

28.8

USAMO 2025Predicted

10.7

Video-MMUPredicted

84.3

browsecompPredicted

85.8

BullshitBenchPredicted

38.3 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

4.0

Arc Agi 2Predicted

0.1

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.9

CAD-EvalPredicted

7.2

Chess PuzzlesPredicted

0.3

CyBenchPredicted

0.2

DeepResearchBenchPredicted

0.4

FictionLiveBenchPredicted

0.4

GdpvalPredicted

0.5

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

8.1

GSOPredicted

0.3

HellaSwagPredicted

0.0

HlePredicted

0.1

Lech Mazur WritingPredicted

7.1

METR Time HorizonsPredicted

6.6

OTIS Mock AIME 2024–2025Predicted

0.0

PIQAPredicted

0.9

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.5

The Agent CompanyPredicted

1.0

TriviaQAPredicted

8.9

VPCTPredicted

0.5

WinoGrandePredicted

0.6

FrontierMathPredicted

36.1 / 100

GAIA Level 1Predicted

11.1

GAIA Level 2Predicted

1.1

GAIA Level 3Predicted

0.0

GAIAPredicted

6.5 / 100

LegalBenchPredicted

32.6 / 100

LiveBench CodingPredicted

76.3 / 100

LiveBench Data AnalysisPredicted

65.3 / 100

LiveBench LanguagePredicted

77.0 / 100

LiveBench MathPredicted

83.3 / 100

LiveBench OverallPredicted

69.5 / 100

LiveBench ReasoningPredicted

72.7 / 100

LongBench v2 EasyPredicted

32.0

LongBench v2 HardPredicted

27.1

LongBench v2Predicted

25.1 / 100

MATH-500Predicted

0.4 / 100

MathVistaPredicted

45.7 / 100

MedQA (USMLE)Predicted

54.9

MLE-benchPredicted

54.4 / 100

MMMUPredicted

58.2 / 100

MMTU Table UnderstandingPredicted

50.5 / 100

MT-BenchPredicted

7.7 / 10

NoLiMa (NIAH)Predicted

84.2 / 100

OCRBench v2Predicted

60.0 / 100

Open LLM AveragePredicted

19.6 / 100

Open LLM: BBHPredicted

44.5 / 100

Open LLM: GPQAPredicted

27.9 / 100

Open LLM: IFEvalPredicted

58.3 / 100

Open LLM: MATH Level 5Predicted

9.5 / 100

Open LLM: MMLU-PROPredicted

28.3 / 100

Open LLM: MUSRPredicted

38.1 / 100

RE-BenchPredicted

99.7

SimpleBenchPredicted

40.6 / 100

simpleqaPredicted

35.5

SWE-bench LitePredicted

11.0 / 100

SWE-bench VerifiedPredicted

47.3 / 100

tau-bench RetailPredicted

90.4 / 100

Vectara Factual ConsistencyPredicted

88.4 / 100

Vectara Hallucination RatePredicted

11.6 / 100

WebArenaPredicted

0.1 / 100

WeirdMLPredicted

22.2 / 100

WildBenchPredicted

30.9