SWE Bench News

Epoch Capabilities Index (ECI)

Other

ARC-AGI

Humanity's Last Exam (HLE)

SWE-Bench

X = 5

X = 10

X = 15

X = 20

X = 30

X = 60

X = 70

X = 50

X = 65

X = 75

X = 80

X = 40

X = 2

X = 4

X = 8

X = 16

X = 32

X = 60

X = 40

X = 50

X = 75

X = 85

X = 70

X = 90

X = 80

90 - 100%

80 - 89%

70 - 79%

50 - 59%

60 - 69%

2026

2027

2025

2028

2029

2030

2031

Other

50-60%

60-70%

NO

NO

NO

2026

2027

2028

2029

2024

2025

95 - 100%

83 - 94%

23 - 34%

35 - 46%

47 - 58%

59 - 70%

71 - 82%

it will make AI models better at agentic tasks (such as OSWorld and SWE-bench)

It will allow AI models to become much better at working with long-context

It will allow AI models to learn at test time

It will allow AI models to hallucinate much less

It will allow AI models to use long context more efficiently

It will make make AI models better at visual reasoning

It will make AI models much better at answering competitive math questions