Opus 4.5 Benchmark Details

Opus 4.5 currently shows benchmark results led by MMLU Pro (2 / 126, score 90), SWE-bench Verified (5 / 105, score 80.90), Terminal Bench Hard (1 / 13, score 44). 3 source links are attached for reference.

Benchmark Results

Opus 4.5

Benchmark Results

综合评估

8 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Extended

2 / 126

GPQA Diamond

Extended

37 / 177

ARC-AGI

Extended

21 / 65

LiveBench

Thinking Level · Medium

74.87

9 / 52

LiveBench

Thinking Level · High

75.58

6 / 52

HLE

Extended

30.80

67 / 154

HLE

ExtendedTools

43.20

36 / 154

ARC-AGI-2

Extended

37.60

26 / 59

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

ExtendedTools

12 / 120

SWE-bench Verified

ExtendedTools

80.90

5 / 105

多模态理解

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU

Extended

80.70

10 / 28

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Extended

3 / 27

Agent能力评测

3 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

ExtendedTools

90.70

21 / 35

τ²-Bench

ExtendedTools

81.99

13 / 40

Terminal Bench Hard

ExtendedTools

1 / 13

数学推理

6 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

Extended

93.30

5 / 14

FrontierMath

Extended

20.70

17 / 60

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

指令跟随

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

ExtendedTools

20 / 29

AI Agent - 工具使用

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench 2.0

ExtendedTools

59.30

20 / 46

OpenClaw智能体能力综合测评

2 evaluations

Benchmark / mode

Score

Rank/total

Claw Bench

ExtendedTools

91.50

7 / 29

Pinch Bench

ExtendedTools

87.20

8 / 37

Compare with other models

Sources

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