Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Sao10K: Llama 3.1 70B Hanami x1 | AgMoDB

Sao10K: Llama 3.1 70B Hanami x1

Last synced Apr 7, 2026, 2:04 PM16K context

Blended Price

$3.00/M

Input Price

$3.00/M

Output Price

$3.00/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Sao10K: Llama 3.1 70B Hanami x1 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

96.4 / 100

Aider PolyglotPredicted

88.2 / 100

AIMEPredicted

1.0 / 30

AIME 2025Predicted

1.0 / 30

AlpacaEval 2.0 LCPredicted

40.6 / 100

AlpacaEval 2.0 RawPredicted

31.4 / 100

ARC-AGI-1Predicted

26.7 / 100

ARC-AGI-1 Cost per TaskPredicted

0.1

ARC-AGI-2Predicted

0.6 / 100

ARC-AGI-2 Cost per TaskPredicted

0.2

BFCL (Berkeley Function Calling)Predicted

66.7

BigCodeBench CompletePredicted

67.1 / 100

BigCodeBench InstructPredicted

56.6 / 100

AA Intelligence Index (Matrix)Predicted

73.5

AA Long Context Reasoning (Matrix)Predicted

70.6

AIME 2024Predicted

99.4

AIME 2025 (Matrix)Predicted

82.4

Arena-Hard AutoPredicted

95.8

BrowseCompPredicted

48.5

BRUMO 2025Predicted

82.6

CMIMC 2025Predicted

86.7

CritPtPredicted

1.1

GPQA Diamond (Matrix)Predicted

92.9

GSM8KPredicted

72.7

HLE (Matrix)Predicted

19.1

HMMT Feb 2025Predicted

72.3

HMMT Nov 2025Predicted

88.4

HumanEvalPredicted

96.7

IFBench (Matrix)Predicted

61.5

IFEvalPredicted

93.8

IMO 2025Predicted

15.8

LiveCodeBench (Matrix)Predicted

89.4

MATH-500 (Matrix)Predicted

99.1

MathArena Apex 2025Predicted

0.5

MMLUPredicted

94.1

MMLU-Pro (Matrix)Predicted

92.0

MMMU-ProPredicted

82.1

MRCR v2Predicted

75.1

OSWorldPredicted

26.7

SimpleQAPredicted

34.5

SMT 2025Predicted

87.2

SWE-bench ProPredicted

32.6

Tau-Bench Telecom (Matrix)Predicted

94.7

Terminal-Bench 2.0Predicted

14.7

Terminal-Bench 1.0Predicted

22.0

USAMO 2025Predicted

18.7

Video-MMUPredicted

87.7

browsecompPredicted

42.0

BullshitBenchPredicted

62.3 / 100

Aider PolyglotPredicted

6.9

Apex AgentsPredicted

1.7

Arc Agi 2Predicted

9.4

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.8

CAD-EvalPredicted

2.2

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.4

DeepResearchBenchPredicted

0.4

FictionLiveBenchPredicted

0.9

GdpvalPredicted

0.2

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

25.1

GSOPredicted

0.0

HellaSwagPredicted

0.1

HlePredicted

0.2

Lech Mazur WritingPredicted

8.6

METR Time HorizonsPredicted

1.9

OTIS Mock AIME 2024–2025Predicted

3.0

PIQAPredicted

0.8

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.3

The Agent CompanyPredicted

3.9

TriviaQAPredicted

15.3

VPCTPredicted

0.4

WinoGrandePredicted

0.9

FrontierMathPredicted

34.0 / 100

GAIA Level 1Predicted

94.8

GAIA Level 2Predicted

96.5

GAIA Level 3Predicted

99.9

GAIAPredicted

89.1 / 100

GPQA DiamondPredicted

0.9 / 100

HLEPredicted

0.2 / 100

IFBenchPredicted

0.7 / 100

LCRPredicted

1.0 / 100

LegalBenchPredicted

96.9 / 100

LiveBench CodingPredicted

64.5 / 100

LiveBench Data AnalysisPredicted

41.8 / 100

LiveBench LanguagePredicted

50.9 / 100

LiveBench MathPredicted

58.8 / 100

LiveBench OverallPredicted

45.1 / 100

LiveBench ReasoningPredicted

40.3 / 100

LiveCodeBenchPredicted

0.9 / 100

LongBench v2 EasyPredicted

67.0

LongBench v2 HardPredicted

59.7

LongBench v2Predicted

48.9 / 100

MATH-500Predicted

1.0 / 100

MathVistaPredicted

66.6 / 100

MedQA (USMLE)Predicted

97.4

MLE-benchPredicted

24.4 / 100

MMLU ProPredicted

0.9 / 100

MMMUPredicted

87.4 / 100

MMTU Table UnderstandingPredicted

68.2 / 100

MT-BenchPredicted

8.1 / 10

OCRBench v2Predicted

92.2 / 100

RE-BenchPredicted

4.2

SciCodePredicted

0.8 / 100

SimpleBenchPredicted

39.8 / 100

simpleqaPredicted

35.6

SWE-bench LitePredicted

66.6 / 100

SWE-bench VerifiedPredicted

60.5 / 100

τ²-BenchPredicted

1.0 / 100

tau-bench RetailPredicted

67.0 / 100

Terminal-Bench HardPredicted

1.0 / 100

Vectara Factual ConsistencyPredicted

92.6 / 100

Vectara Hallucination RatePredicted

7.4 / 100

WebArenaPredicted

36.2 / 100

WeirdMLPredicted

68.1 / 100

WildBenchPredicted

58.8

Epoch Capabilities Indexepoch_ai

125.5

NoLiMa (NIAH)nolima

94.5 / 100

Open LLM Averageopen_llm_leaderboard

26.2 / 100

Open LLM: BBHopen_llm_leaderboard

62.6 / 100

Open LLM: GPQAopen_llm_leaderboard

38.8 / 100

Open LLM: IFEvalopen_llm_leaderboard

16.8 / 100

Open LLM: MATH Level 5open_llm_leaderboard

18.4 / 100

Open LLM: MMLU-PROopen_llm_leaderboard

46.5 / 100

Open LLM: MUSRopen_llm_leaderboard

45.7 / 100