Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Meta: Llama 3 70B Instruct | AgMoDB

Meta: Llama 3 70B Instruct

Last synced Apr 7, 2026, 2:04 PM8K context

Blended Price

$0.57/M

Input Price

$0.51/M

Output Price

$0.74/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AlpacaEval 2.0 LC

How Meta: Llama 3 70B Instruct 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

alpacaeval

34.4 / 100

AlpacaEval 2.0 Rawalpacaeval

33.2 / 100

AA-Omniscience AccuracyPredicted

41.4 / 100

AA-Omniscience Hallucination RatePredicted

95.0 / 100

Aider PolyglotPredicted

22.6 / 100

AIMEPredicted

0.1 / 30

AIME 2025Predicted

0.1 / 30

ARC-AGI-1Predicted

5.0 / 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

25.5

AA Intelligence Index (Matrix)Predicted

83.2

AA Long Context Reasoning (Matrix)Predicted

55.4

AIME 2024Predicted

73.3

AIME 2025 (Matrix)Predicted

42.3

Arena-Hard AutoPredicted

61.4

BrowseCompPredicted

24.9

BRUMO 2025Predicted

91.6

CMIMC 2025Predicted

86.5

CritPtPredicted

0.2

GPQA Diamond (Matrix)Predicted

56.8

GSM8KPredicted

91.1

HLE (Matrix)Predicted

45.9

HMMT Feb 2025Predicted

42.2

HMMT Nov 2025Predicted

89.2

HumanEvalPredicted

80.8

IFBench (Matrix)Predicted

32.7

IFEvalPredicted

81.6

IMO 2025Predicted

12.9

LiveCodeBench (Matrix)Predicted

46.0

MATH-500 (Matrix)Predicted

94.8

MathArena Apex 2025Predicted

0.9

MMLUPredicted

80.5

MMLU-Pro (Matrix)Predicted

68.0

MMMU-ProPredicted

80.6

MRCR v2Predicted

75.0

OSWorldPredicted

44.4

SimpleQAPredicted

23.0

SMT 2025Predicted

68.2

SWE-bench ProPredicted

37.7

Tau-Bench Telecom (Matrix)Predicted

95.7

Terminal-Bench 2.0Predicted

9.4

Terminal-Bench 1.0Predicted

25.9

USAMO 2025Predicted

2.4

Video-MMUPredicted

94.0

browsecompPredicted

70.2

BullshitBenchPredicted

46.7 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

1.9

Arc Agi 2Predicted

0.0

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.9

CAD-EvalPredicted

8.2

Chess PuzzlesPredicted

0.1

DeepResearchBenchPredicted

0.3

FictionLiveBenchPredicted

0.4

GdpvalPredicted

0.1

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

5.4

GSOPredicted

0.0

HellaSwagPredicted

19.6

HlePredicted

0.2

Lech Mazur WritingPredicted

7.0

METR Time HorizonsPredicted

0.2

PIQAPredicted

0.9

PosttrainbenchPredicted

60.0

SimpleQA Verified (Epoch)Predicted

0.4

The Agent CompanyPredicted

1.3

TriviaQAPredicted

4.1

VPCTPredicted

0.3

FrontierMathPredicted

36.1 / 100

GPQA DiamondPredicted

0.5 / 100

HLEPredicted

0.0 / 100

IFBenchPredicted

0.3 / 100

LCRPredicted

0.0 / 100

LegalBenchPredicted

68.8 / 100

LiveBench CodingPredicted

65.6 / 100

LiveBench Data AnalysisPredicted

42.1 / 100

LiveBench LanguagePredicted

51.9 / 100

LiveBench MathPredicted

60.3 / 100

LiveBench OverallPredicted

18.4 / 100

LiveBench ReasoningPredicted

38.4 / 100

LiveCodeBenchPredicted

0.3 / 100

LongBench v2 EasyPredicted

41.4

LongBench v2 HardPredicted

38.8

LongBench v2Predicted

30.3 / 100

MATH-500Predicted

0.8 / 100

MathVistaPredicted

49.0 / 100

MedQA (USMLE)Predicted

74.1

MLE-benchPredicted

13.4 / 100

MMLU ProPredicted

0.7 / 100

MMMUPredicted

59.1 / 100

MMTU Table UnderstandingPredicted

48.1 / 100

MT-BenchPredicted

8.4 / 10

NoLiMa (NIAH)Predicted

91.4 / 100

OCRBench v2Predicted

73.1 / 100

RE-BenchPredicted

1.3

SciCodePredicted

0.2 / 100

SimpleBenchPredicted

23.5 / 100

simpleqaPredicted

21.4

SWE-bench LitePredicted

47.7 / 100

SWE-bench VerifiedPredicted

29.1 / 100

τ²-BenchPredicted

0.0 / 100

tau-bench RetailPredicted

77.6 / 100

Terminal-Bench HardPredicted

0.0 / 100

Vectara Factual ConsistencyPredicted

92.2 / 100

Vectara Hallucination RatePredicted

7.8 / 100

WebArenaPredicted

3.9 / 100

WeirdMLPredicted

21.9 / 100

BigCodeBench Completebigcodebench

54.5 / 100

BigCodeBench Instructbigcodebench

43.6 / 100

CyBenchepoch_ai

0.1

Epoch Capabilities Indexepoch_ai

119.5

OpenBookQAepoch_ai

0.5

OTIS Mock AIME 2024–2025epoch_ai

0.0

WinoGrandeepoch_ai

0.8

GAIA Level 1gaia

30.2

GAIA Level 2gaia

11.6

GAIA Level 3gaia

7.7

GAIAgaia

17.0 / 100

Open LLM Averageopen_llm_leaderboard

36.4 / 100

Open LLM: BBHopen_llm_leaderboard

65.5 / 100

Open LLM: GPQAopen_llm_leaderboard

28.7 / 100

Open LLM: IFEvalopen_llm_leaderboard

81.0 / 100

Open LLM: MATH Level 5open_llm_leaderboard

24.5 / 100

Open LLM: MMLU-PROopen_llm_leaderboard

52.1 / 100

Open LLM: MUSRopen_llm_leaderboard

41.5 / 100

WildBenchwildbench

49.6