Opus 4.1 Benchmark Details

Opus 4.1 currently shows benchmark results led by MMLU Pro (7 / 133, score 88), Terminal-Bench (5 / 35, score 46.50), SimpleBench (19 / 67, score 60). 1 source link is attached for reference.

Benchmark Results

Opus 4.1

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Extended

7 / 133

LiveBench

Standard Mode

54.45

82 / 115

LiveBench

32K

61.81

60 / 115

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Extended

135 / 270

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

ExtendedTools

74.50

41 / 114

Math and Reasoning

9 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Extended

60 / 106

IMO 2024

Standard Mode

18.70

3 / 10

FrontierMath v2

32K

12.63

56 / 58

IMO 2025

Standard Mode

11.70

4 / 9

FrontierMath

Standard Mode

5.90

35 / 60

FrontierMath

Extended

7.20

33 / 60

FrontierMath - Tier 4

32K

4.20

40 / 80

FrontierMath - Tier 4

Extended

4.20

40 / 80

FrontierMath Tier 4 v2

32K

2.44

35 / 40

AI Agent - Tool Usage

2 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench

Extended

46.50

5 / 35

Terminal-Bench

ExtendedTools

43.30

9 / 35

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Extended

19 / 67

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

ExtendedTools

27 / 34

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench Hard

ExtendedTools

9 / 13

Compare with other models

Sources

anthropic.comanthropic.com