Opus 4.5 Benchmark Details

Opus 4.5 currently shows benchmark results led by MMLU Pro (2 / 133, score 90), Terminal Bench Hard (1 / 13, score 44), SWE-bench Verified (9 / 114, score 80.90). 3 source links are attached for reference.

Benchmark Results

Opus 4.5

Benchmark Results

General Knowledge

9 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Extended

2 / 133

ARC-AGI

Extended

24 / 68

LiveBench

64K

75.96

11 / 115

LiveBench

Thinking Level · Low

55.77

80 / 115

LiveBench

Thinking Level · Medium

59.10

72 / 115

LiveBench

Thinking Level · High

58.59

74 / 115

HLE

Extended

30.80

88 / 181

HLE

ExtendedTools

43.20

52 / 181

ARC-AGI-2

Extended

37.60

29 / 62

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Extended

70 / 224

Coding and Software Engineer

6 evaluations

Benchmark / mode

Score

Rank/total

Text Arena (Coding)

Standard Mode

1479

20 / 35

Text Arena (Coding)

32K

1512

17 / 35

LiveCodeBench

ExtendedTools

14 / 126

SWE-bench Verified

ExtendedTools

80.90

9 / 114

WeirdML v2

16KTools

63.70

24 / 52

GSO

Standard ModeTools

26.50

8 / 21

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1683.20

25 / 99

Multimodal Understanding

3 evaluations

Benchmark / mode

Score

Rank/total

MMMU

Extended

80.70

10 / 28

GeoBench ACW

Standard Mode

10 / 20

VPCT

32K

15 / 24

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Extended

14 / 67

Agent Level Benchmark

7 evaluations

Benchmark / mode

Score

Rank/total

METR Time Horizons v1.1

Standard ModeTools

293

6 / 22

METR Time Horizons v1.1

16KTools

288.90

7 / 22

τ²-Bench - Telecom

ExtendedTools

90.70

21 / 35

τ²-Bench

ExtendedTools

81.99

13 / 43

Terminal Bench Hard

ExtendedTools

1 / 13

BALROG

Standard ModeTools

43.50

5 / 12

BALROG

64KTools

7 / 12

Math and Reasoning

8 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

Extended

93.30

8 / 19

FrontierMath v2

32K

34.39

30 / 34

FrontierMath

Extended

20.70

17 / 60

FrontierMath Tier 4 v2

32K

4.88

28 / 34

FrontierMath - Tier 4

Standard Mode

4.20

40 / 80

FrontierMath - Tier 4

16K

2.10

56 / 80

FrontierMath - Tier 4

32K

4.20

40 / 80

FrontierMath - Tier 4

Extended

4.20

40 / 80

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

ExtendedTools

24 / 33

AI Agent - Tool Usage

2 evaluations

Benchmark / mode

Score

Rank/total

MCP-Atlas

Thinking Level · HighTools

69.80

27 / 39

Terminal Bench 2.0

ExtendedTools

59.30

20 / 48

Claw-style Agent Evaluation

2 evaluations

Benchmark / mode

Score

Rank/total

Claw Bench

ExtendedTools

91.50

7 / 29

Pinch Bench

ExtendedTools

87.20

9 / 38

Long Context

1 evaluations

Benchmark / mode

Score

Rank/total

LongBench v2

Standard Mode

64.40

2 / 13

Compare with other models

Sources

pinchbench.compinchbench.com anthropic.comanthropic.com epoch.aiepoch.ai