APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
newsBenchmarksLlms

Epoch Finds Half of 21 Major AI Benchmarks Are Flawed

Epoch AI expanded its benchmark audit program, flagging popular evals like SWE-bench Verified and Humanity's Last Exam as Flawed under a public rubric.

Epoch Finds Half of 21 Major AI Benchmarks Are Flawed
Source
Epoch AI
Published
Author
AlphaSignal Newsroom
Read
1 min read

Epoch AI expanded its benchmark audit program, flagging popular evals like SWE-bench Verified and Humanity's Last Exam as Flawed under a public rubric.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Moonshot's Kimi K3.1 Pro Tops Every Public API Model in Security Benchmarks
Artificial Analysis · news

Moonshot's Kimi K3.1 Pro Tops Every Public API Model in Security Benchmarks

DeepSeek's V4.1 Flash 1017 Tops Public Cybersecurity Rankings at $0.42 per Task
Artificial Analysis · news

DeepSeek's V4.1 Flash 1017 Tops Public Cybersecurity Rankings at $0.42 per Task

Mistral's Timestral Beats Larger Rivals at Zero-Shot Forecasting on CPUs
Mistral AI · model

Mistral's Timestral Beats Larger Rivals at Zero-Shot Forecasting on CPUs