Claude Opus 4.5 (Reasoning)

November 24, 2025Last synced Apr 7, 2026, 4:00 PM

Blended Price

$10.00/M

Input Price

$5.00/M

Output Price

$25.00/M

Speed

67 tok/s

TTFT

12.24s

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Claude Opus 4.5 (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

GPQA Diamond

0.9 / 100

LiveCodeBench

0.9 / 100

Terminal-Bench Hard

0.5 / 100

τ²-Bench

0.9 / 100

ARC-AGI-1arc_agi

80.0 / 100

ARC-AGI-1 Cost per Taskarc_agi

1.5

ARC-AGI-2arc_agi

37.6 / 100

ARC-AGI-2 Cost per Taskarc_agi

2.4

ARC-AGI-1benchmark_matrix

80.0 / 100

ARC-AGI-2benchmark_matrix

37.6 / 100

AA Long Context Reasoning (Matrix)benchmark_matrix

75.0

AIME 2024benchmark_matrix

90.0

AIME 2025 (Matrix)benchmark_matrix

92.8

Arena-Hard Autobenchmark_matrix

59.7

BrowseCompbenchmark_matrix

67.8

Chatbot Arena ELO (Matrix)benchmark_matrix

1468.0

Codeforces Ratingbenchmark_matrix

2070.0

CritPtbenchmark_matrix

0.3

GPQA Diamond (Matrix)benchmark_matrix

87.0

HLE (Matrix)benchmark_matrix

37.6

HMMT Feb 2025benchmark_matrix

92.9

HumanEvalbenchmark_matrix

95.1

IFEvalbenchmark_matrix

90.0

LiveCodeBench (Matrix)benchmark_matrix

68.0

MATH-500 (Matrix)benchmark_matrix

85.0

MMLUbenchmark_matrix

90.8

MMLU-Pro (Matrix)benchmark_matrix

80.0

OSWorldbenchmark_matrix

66.3

SimpleQAbenchmark_matrix

72.0

SWE-bench Probenchmark_matrix

45.9

Tau-Bench Telecom (Matrix)benchmark_matrix

98.2

Terminal-Bench 2.0benchmark_matrix

57.8

Terminal-Bench 1.0benchmark_matrix

39.0

Video-MMUbenchmark_matrix

68.4

browsecompbenchmark_matrix

67.8

FrontierMathbenchmark_matrix

21.0 / 100

LiveBench Overallbenchmark_matrix

76.0 / 100

MMMUbenchmark_matrix

80.7 / 100

SimpleBenchbenchmark_matrix

62.0 / 100

simpleqabenchmark_matrix

72.0

SWE-bench Verifiedbenchmark_matrix

80.9 / 100

tau-bench Retailbenchmark_matrix

88.9 / 100

AA-Omniscience Hallucination RatePredicted

97.5 / 100

Aider PolyglotPredicted

81.8 / 100

AIMEPredicted

0.4 / 30

AlpacaEval 2.0 LCPredicted

69.9 / 100

AlpacaEval 2.0 RawPredicted

67.8 / 100

BigCodeBench CompletePredicted

53.3 / 100

BigCodeBench InstructPredicted

43.1 / 100

AA Intelligence Index (Matrix)Predicted

62.6

BRUMO 2025Predicted

99.0

CMIMC 2025Predicted

96.5

HMMT Nov 2025Predicted

95.6

IFBench (Matrix)Predicted

67.9

IMO 2025Predicted

38.7

MathArena Apex 2025Predicted

2.0

MMMU-ProPredicted

80.9

MRCR v2Predicted

88.8

SMT 2025Predicted

91.9

USAMO 2025Predicted

25.5

Aider PolyglotPredicted

0.1

BIG-Bench HardPredicted

3.0

CAD-EvalPredicted

2.7

DeepResearchBenchPredicted

0.5

FictionLiveBenchPredicted

0.9

GSM8K (Epoch)Predicted

2.2

HellaSwagPredicted

0.0

Lech Mazur WritingPredicted

8.6

The Agent CompanyPredicted

56.9

TriviaQAPredicted

14.7

WinoGrandePredicted

1.2

GAIA Level 1Predicted

78.2

GAIA Level 2Predicted

61.8

GAIA Level 3Predicted

69.4

GAIAPredicted

63.0 / 100

LiveBench CodingPredicted

75.4 / 100

LiveBench Data AnalysisPredicted

67.5 / 100

LiveBench LanguagePredicted

74.1 / 100

LiveBench MathPredicted

80.7 / 100

LiveBench ReasoningPredicted

78.1 / 100

LongBench v2 EasyPredicted

67.3

LongBench v2 HardPredicted

44.9

LongBench v2Predicted

40.9 / 100

MATH-500Predicted

0.9 / 100

MathVistaPredicted

61.6 / 100

MedQA (USMLE)Predicted

93.5

MLE-benchPredicted

56.6 / 100

MMTU Table UnderstandingPredicted

69.5 / 100

MT-BenchPredicted

8.2 / 10

NoLiMa (NIAH)Predicted

93.6 / 100

OCRBench v2Predicted

82.5 / 100

Open LLM AveragePredicted

10.6 / 100

Open LLM: BBHPredicted

39.7 / 100

Open LLM: GPQAPredicted

27.3 / 100

Open LLM: IFEvalPredicted

24.3 / 100

Open LLM: MATH Level 5Predicted

28.0 / 100

Open LLM: MMLU-PROPredicted

21.6 / 100

Open LLM: MUSRPredicted

38.4 / 100

SWE-bench LitePredicted

52.4 / 100

WebArenaPredicted

12.6 / 100

WildBenchPredicted

40.9

BFCL (Berkeley Function Calling)bfcl

77.5

browsecompbrowsecomp

67.8

BullshitBenchbullshitbench

90.0 / 100

Arena ELO: Codingchatbot_arena

1489.0

Chatbot Arena ELOchatbot_arena

1474.0

Apex Agentsepoch_ai

3.1

Arc Agi 2epoch_ai

0.1

Chess Puzzlesepoch_ai

0.1

Epoch Capabilities Indexepoch_ai

149.7

GeoBenchepoch_ai

0.0

METR Time Horizonsepoch_ai

49.4

OSWorld (Epoch)epoch_ai

66.3

OTIS Mock AIME 2024–2025epoch_ai

0.8

Posttrainbenchepoch_ai

0.0

SimpleQA Verified (Epoch)epoch_ai

0.4

WebDev Arenaepoch_ai

4468.0

LegalBenchlegalbench

84.6 / 100

OpenRouter Token Volumeopenrouter_rankings

157000000000.0

OpenRouter Weekly Trendopenrouter_rankings

14.0

RE-Benchrebench

97.8

SimpleBenchsimplebench

62.0 / 100

SWE-bench Verifiedswebench

74.4 / 100

Vectara Factual Consistencyvectara_hallucination

89.1 / 100

Vectara Hallucination Ratevectara_hallucination

10.9 / 100

WeirdMLweirdml

63.7 / 100