Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Qwen2.5 72B Instruct | AgMoDB

Qwen2.5 72B Instruct

Last synced Apr 7, 2026, 2:04 PM33K context

Blended Price

$0.19/M

Input Price

$0.12/M

Output Price

$0.39/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Qwen2.5 72B 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

Predicted

39.0 / 100

AA-Omniscience Hallucination RatePredicted

94.1 / 100

Aider PolyglotPredicted

22.6 / 100

AIMEPredicted

0.4 / 30

AIME 2025Predicted

0.3 / 30

AlpacaEval 2.0 LCPredicted

40.8 / 100

AlpacaEval 2.0 RawPredicted

32.1 / 100

ARC-AGI-1Predicted

3.5 / 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

30.0

AA Intelligence Index (Matrix)Predicted

68.4

AA Long Context Reasoning (Matrix)Predicted

77.2

AIME 2024Predicted

54.3

AIME 2025 (Matrix)Predicted

27.4

Arena-Hard AutoPredicted

64.2

BrowseCompPredicted

52.9

BRUMO 2025Predicted

62.7

CMIMC 2025Predicted

82.9

CritPtPredicted

0.1

GPQA Diamond (Matrix)Predicted

58.4

GSM8KPredicted

61.7

HLE (Matrix)Predicted

63.7

HMMT Feb 2025Predicted

33.1

HMMT Nov 2025Predicted

87.3

HumanEvalPredicted

84.7

IFBench (Matrix)Predicted

30.9

IFEvalPredicted

80.7

IMO 2025Predicted

8.4

LiveCodeBench (Matrix)Predicted

51.9

MATH-500 (Matrix)Predicted

90.5

MathArena Apex 2025Predicted

0.4

MMLUPredicted

82.6

MMLU-Pro (Matrix)Predicted

69.5

MMMU-ProPredicted

81.8

MRCR v2Predicted

76.0

OSWorldPredicted

29.4

SimpleQAPredicted

16.8

SMT 2025Predicted

70.0

SWE-bench ProPredicted

55.7

Tau-Bench Telecom (Matrix)Predicted

93.8

Terminal-Bench 2.0Predicted

19.2

Terminal-Bench 1.0Predicted

11.7

USAMO 2025Predicted

4.8

Video-MMUPredicted

86.4

browsecompPredicted

48.8

BullshitBenchPredicted

61.2 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

1.9

Arc Agi 2Predicted

19.4

BoolQPredicted

0.9

CAD-EvalPredicted

4.1

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.1

DeepResearchBenchPredicted

4.5

FictionLiveBenchPredicted

0.4

GdpvalPredicted

0.1

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

33.2

GSOPredicted

0.0

HlePredicted

0.2

Lech Mazur WritingPredicted

7.0

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.2

VPCTPredicted

0.3

FrontierMathPredicted

43.0 / 100

GAIA Level 1Predicted

38.9

GAIA Level 2Predicted

19.6

GAIA Level 3Predicted

0.6

GAIAPredicted

25.5 / 100

GPQA DiamondPredicted

0.5 / 100

HLEPredicted

0.0 / 100

IFBenchPredicted

0.3 / 100

LCRPredicted

0.1 / 100

LegalBenchPredicted

87.9 / 100

LiveBench CodingPredicted

69.5 / 100

LiveBench Data AnalysisPredicted

42.9 / 100

LiveBench LanguagePredicted

59.9 / 100

LiveBench MathPredicted

60.3 / 100

LiveBench OverallPredicted

47.4 / 100

LiveBench ReasoningPredicted

47.4 / 100

LiveCodeBenchPredicted

0.3 / 100

LongBench v2 EasyPredicted

44.7

LongBench v2 HardPredicted

43.0

LongBench v2Predicted

33.4 / 100

MATH-500Predicted

0.9 / 100

MathVistaPredicted

56.6 / 100

MedQA (USMLE)Predicted

76.7

MLE-benchPredicted

10.2 / 100

MMLU ProPredicted

0.7 / 100

MMMUPredicted

65.2 / 100

MMTU Table UnderstandingPredicted

45.8 / 100

MT-BenchPredicted

7.9 / 10

NoLiMa (NIAH)Predicted

93.0 / 100

OCRBench v2Predicted

81.8 / 100

RE-BenchPredicted

0.0

SciCodePredicted

0.4 / 100

SimpleBenchPredicted

19.0 / 100

simpleqaPredicted

18.3

SWE-bench LitePredicted

57.1 / 100

SWE-bench VerifiedPredicted

32.6 / 100

τ²-BenchPredicted

0.0 / 100

tau-bench RetailPredicted

71.5 / 100

Terminal-Bench HardPredicted

0.0 / 100

Vectara Factual ConsistencyPredicted

92.2 / 100

Vectara Hallucination RatePredicted

7.8 / 100

WebArenaPredicted

38.3 / 100

WeirdMLPredicted

18.5 / 100

WildBenchPredicted

54.4

BigCodeBench Completebigcodebench

55.9 / 100

BigCodeBench Instructbigcodebench

45.8 / 100

BALROGepoch_ai

0.0

BIG-Bench Hardepoch_ai

3.0

Epoch Capabilities Indexepoch_ai

129.5

HellaSwagepoch_ai

10.0

METR Time Horizonsepoch_ai

0.4

OTIS Mock AIME 2024–2025epoch_ai

0.1

PIQAepoch_ai

0.8

The Agent Companyepoch_ai

1.5

TriviaQAepoch_ai

5.0

WinoGrandeepoch_ai

0.8

EQ-Bench 3eqbench

1221.0

HuggingFace Downloads (30d)hf-downloads

367168.0

HuggingFace Likeshf-downloads

76.0

Open LLM Averageopen_llm_leaderboard

46.3 / 100

Open LLM: BBHopen_llm_leaderboard

71.5 / 100

Open LLM: GPQAopen_llm_leaderboard

40.7 / 100

Open LLM: IFEvalopen_llm_leaderboard

71.5 / 100

Open LLM: MATH Level 5open_llm_leaderboard

52.4 / 100

Open LLM: MMLU-PROopen_llm_leaderboard

58.7 / 100

Open LLM: MUSRopen_llm_leaderboard

47.2 / 100