Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Claude 4.5 Sonnet (Reasoning) | AgMoDB

Claude 4.5 Sonnet (Reasoning)

September 29, 2025Last synced Apr 7, 2026, 4:00 PM

Blended Price

$6.00/M

Input Price

$3.00/M

Output Price

$15.00/M

Speed

56 tok/s

TTFT

7.78s

Benchmark Scores

Intelligence Index

External Benchmarks

AlpacaEval 2.0 LC

How Claude 4.5 Sonnet (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

43.0

Coding Index

38.6

Math Index

88.0

MMLU Pro

0.9 / 100

GPQA Diamond

0.8 / 100

HLE

0.2 / 100

LiveCodeBench

0.7 / 100

SciCode

0.4 / 100

MATH-500

— / 100

AIME

— / 30

AIME 2025

0.9 / 30

IFBench

0.6 / 100

LCR

0.7 / 100

Terminal-Bench Hard

0.4 / 100

τ²-Bench

0.8 / 100

alpacaeval

27.3 / 100

AlpacaEval 2.0 Rawalpacaeval

17.0 / 100

AA-Omniscience AccuracyPredicted

44.7 / 100

AA-Omniscience Hallucination RatePredicted

97.6 / 100

Aider PolyglotPredicted

82.8 / 100

AIMEPredicted

0.3 / 30

ARC-AGI-1Predicted

81.6 / 100

ARC-AGI-1 Cost per TaskPredicted

0.7

ARC-AGI-2Predicted

31.7 / 100

ARC-AGI-2 Cost per TaskPredicted

1.6

BFCL (Berkeley Function Calling)Predicted

53.7

BigCodeBench CompletePredicted

47.7 / 100

BigCodeBench InstructPredicted

37.1 / 100

AA Intelligence Index (Matrix)Predicted

62.1

AA Long Context Reasoning (Matrix)Predicted

75.5

AIME 2024Predicted

87.7

AIME 2025 (Matrix)Predicted

99.9

Arena-Hard AutoPredicted

66.5

BrowseCompPredicted

75.6

BRUMO 2025Predicted

99.2

CMIMC 2025Predicted

91.9

CritPtPredicted

7.2

GPQA Diamond (Matrix)Predicted

88.8

GSM8KPredicted

95.6

HLE (Matrix)Predicted

37.4

HMMT Feb 2025Predicted

93.7

HMMT Nov 2025Predicted

92.9

HumanEvalPredicted

93.8

IFBench (Matrix)Predicted

63.2

IFEvalPredicted

91.4

IMO 2025Predicted

16.6

LiveCodeBench (Matrix)Predicted

82.6

MATH-500 (Matrix)Predicted

96.0

MathArena Apex 2025Predicted

5.6

MMLUPredicted

90.5

MMLU-Pro (Matrix)Predicted

86.4

MMMU-ProPredicted

80.8

MRCR v2Predicted

80.4

OSWorldPredicted

57.6

SimpleQAPredicted

56.7

SMT 2025Predicted

36.9

SWE-bench ProPredicted

48.3

Tau-Bench Telecom (Matrix)Predicted

98.3

Terminal-Bench 2.0Predicted

54.7

Terminal-Bench 1.0Predicted

41.4

USAMO 2025Predicted

26.3

Video-MMUPredicted

86.1

browsecompPredicted

80.4

BullshitBenchPredicted

41.8 / 100

Aider PolyglotPredicted

0.2

Apex AgentsPredicted

3.0

Arc Agi 2Predicted

0.4

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.7

CAD-EvalPredicted

8.6

Chess PuzzlesPredicted

0.3

CyBenchPredicted

0.2

DeepResearchBenchPredicted

0.5

FictionLiveBenchPredicted

0.8

GdpvalPredicted

0.5

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

3.1

GSOPredicted

0.1

HellaSwagPredicted

0.0

HlePredicted

0.3

Lech Mazur WritingPredicted

8.5

METR Time HorizonsPredicted

49.2

OTIS Mock AIME 2024–2025Predicted

0.9

PIQAPredicted

0.8

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.5

The Agent CompanyPredicted

2.7

TriviaQAPredicted

9.1

VPCTPredicted

0.4

WinoGrandePredicted

0.9

FrontierMathPredicted

30.0 / 100

GAIA Level 1Predicted

77.5

GAIA Level 2Predicted

59.7

GAIA Level 3Predicted

65.7

GAIAPredicted

62.0 / 100

LiveBench CodingPredicted

75.0 / 100

LiveBench Data AnalysisPredicted

63.9 / 100

LiveBench LanguagePredicted

75.3 / 100

LiveBench MathPredicted

81.7 / 100

LiveBench OverallPredicted

68.7 / 100

LiveBench ReasoningPredicted

72.6 / 100

LongBench v2 EasyPredicted

54.4

LongBench v2 HardPredicted

44.3

LongBench v2Predicted

40.4 / 100

MATH-500Predicted

1.0 / 100

MathVistaPredicted

57.8 / 100

MedQA (USMLE)Predicted

92.6

MLE-benchPredicted

58.8 / 100

MMMUPredicted

79.2 / 100

MMTU Table UnderstandingPredicted

66.9 / 100

NoLiMa (NIAH)Predicted

93.4 / 100

OCRBench v2Predicted

82.0 / 100

Open LLM AveragePredicted

15.4 / 100

Open LLM: BBHPredicted

43.3 / 100

Open LLM: GPQAPredicted

28.2 / 100

Open LLM: IFEvalPredicted

33.5 / 100

Open LLM: MATH Level 5Predicted

5.8 / 100

Open LLM: MMLU-PROPredicted

27.4 / 100

Open LLM: MUSRPredicted

42.0 / 100

RE-BenchPredicted

99.9

simpleqaPredicted

52.8

SWE-bench LitePredicted

52.4 / 100

tau-bench RetailPredicted

88.6 / 100

Vectara Factual ConsistencyPredicted

89.1 / 100

Vectara Hallucination RatePredicted

10.9 / 100

WeirdMLPredicted

62.4 / 100

WildBenchPredicted

34.9

LegalBenchlegalbench

10.0 / 100

MT-Benchmtbench

7.9 / 10

SimpleBenchsimplebench

54.3 / 100

SWE-bench Verifiedswebench

70.6 / 100

WebArenawebarena

7.1 / 100