Claude 3 Sonnet

March 4, 2024Last synced Apr 7, 2026, 4:00 PM

Blended Price

$6.00/M

Input Price

$3.00/M

Output Price

$15.00/M

Speed

0 tok/s

TTFT

0.00s

Benchmark Scores

Intelligence Index

External Benchmarks

AlpacaEval 2.0 LC

How Claude 3 Sonnet 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

GPQA Diamond

0.4 / 100

LiveCodeBench

0.2 / 100

Terminal-Bench Hard

— / 100

τ²-Bench

— / 100

AlpacaEval 2.0 Rawalpacaeval

25.6 / 100

AA-Omniscience AccuracyPredicted

42.2 / 100

AA-Omniscience Hallucination RatePredicted

97.3 / 100

Aider PolyglotPredicted

11.8 / 100

AIME 2025Predicted

0.1 / 30

ARC-AGI-1Predicted

4.2 / 100

ARC-AGI-1 Cost per TaskPredicted

0.0

ARC-AGI-2Predicted

2.7 / 100

ARC-AGI-2 Cost per TaskPredicted

0.0

BFCL (Berkeley Function Calling)Predicted

27.7

AA Intelligence Index (Matrix)Predicted

62.8

AA Long Context Reasoning (Matrix)Predicted

70.8

AIME 2024Predicted

24.6

AIME 2025 (Matrix)Predicted

17.3

Arena-Hard AutoPredicted

53.1

BrowseCompPredicted

64.6

BRUMO 2025Predicted

82.3

CMIMC 2025Predicted

70.8

GPQA Diamond (Matrix)Predicted

43.3

HLE (Matrix)Predicted

11.7

HMMT Feb 2025Predicted

29.5

HMMT Nov 2025Predicted

89.3

HumanEvalPredicted

76.6

IFBench (Matrix)Predicted

26.6

IFEvalPredicted

79.3

IMO 2025Predicted

11.8

LiveCodeBench (Matrix)Predicted

33.1

MATH-500 (Matrix)Predicted

92.5

MathArena Apex 2025Predicted

1.0

MMLU-Pro (Matrix)Predicted

62.1

MMMU-ProPredicted

78.9

MRCR v2Predicted

74.8

OSWorldPredicted

33.2

SimpleQAPredicted

19.9

SMT 2025Predicted

78.0

SWE-bench ProPredicted

26.3

Tau-Bench Telecom (Matrix)Predicted

95.8

Terminal-Bench 2.0Predicted

22.9

Terminal-Bench 1.0Predicted

12.7

USAMO 2025Predicted

4.3

Video-MMUPredicted

85.5

browsecompPredicted

72.8

BullshitBenchPredicted

13.0 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

2.4

Arc Agi 2Predicted

0.0

BIG-Bench HardPredicted

3.0

CAD-EvalPredicted

9.4

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.1

DeepResearchBenchPredicted

0.3

FictionLiveBenchPredicted

0.3

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

6.5

HellaSwagPredicted

8.3

Lech Mazur WritingPredicted

6.7

METR Time HorizonsPredicted

0.3

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.4

The Agent CompanyPredicted

1.0

TriviaQAPredicted

2.5

FrontierMathPredicted

13.4 / 100

GAIA Level 1Predicted

16.7

GAIA Level 2Predicted

7.6

GAIA Level 3Predicted

0.0

GAIAPredicted

10.6 / 100

IFBenchPredicted

0.2 / 100

LCRPredicted

0.0 / 100

LegalBenchPredicted

70.4 / 100

LiveBench CodingPredicted

65.6 / 100

LiveBench Data AnalysisPredicted

41.5 / 100

LiveBench LanguagePredicted

51.4 / 100

LiveBench MathPredicted

59.9 / 100

LiveBench OverallPredicted

43.9 / 100

LiveBench ReasoningPredicted

37.0 / 100

LongBench v2 EasyPredicted

35.7

LongBench v2 HardPredicted

34.4

LongBench v2Predicted

31.3 / 100

MedQA (USMLE)Predicted

67.6

MLE-benchPredicted

12.9 / 100

MMTU Table UnderstandingPredicted

41.2 / 100

MT-BenchPredicted

8.2 / 10

NoLiMa (NIAH)Predicted

89.3 / 100

OCRBench v2Predicted

72.3 / 100

Open LLM AveragePredicted

39.9 / 100

Open LLM: BBHPredicted

64.5 / 100

Open LLM: GPQAPredicted

33.9 / 100

Open LLM: IFEvalPredicted

76.9 / 100

Open LLM: MATH Level 5Predicted

39.7 / 100

Open LLM: MMLU-PROPredicted

49.4 / 100

Open LLM: MUSRPredicted

43.5 / 100

RE-BenchPredicted

0.8

SimpleBenchPredicted

19.2 / 100

simpleqaPredicted

17.7

SWE-bench LitePredicted

63.3 / 100

SWE-bench VerifiedPredicted

27.5 / 100

τ²-BenchPredicted

0.1 / 100

tau-bench RetailPredicted

62.2 / 100

Terminal-Bench HardPredicted

0.0 / 100

Vectara Factual ConsistencyPredicted

92.6 / 100

Vectara Hallucination RatePredicted

7.4 / 100

WebArenaPredicted

2.9 / 100

BigCodeBench Completebigcodebench

53.8 / 100

BigCodeBench Instructbigcodebench

42.7 / 100

Epoch Capabilities Indexepoch_ai

120.1

OTIS Mock AIME 2024–2025epoch_ai

0.0

WinoGrandeepoch_ai

0.8

MathVistamathvista

47.9 / 100

WeirdMLweirdml

10.2 / 100

WildBenchwildbench

45.2