Author

Tony Duan

Published

March 18, 2025

(LLM)Large language model

Code

library(tidyverse)
library(openxlsx)
library(readxl)

Code

data001=read_excel('AI model.xlsx')
head(data001)

LLM model performance

math

AIME

https://en.wikipedia.org/wiki/American_Invitational_Mathematics_Examination

MATH-500

Code

Codeforces

LiveCodeBench

English

MMLU

Measuring Massive Multitask Language Understanding (MMLU)

https://en.wikipedia.org/wiki/MMLU

Science

GPQA-Diamond

Graduate-Level Google-Proof Q&A

Description: GPQA consists of 448 multiple-choice questions meticulously crafted by domain experts in biology, physics, and chemistry. These questions are intentionally designed to be high-quality and extremely difficult.

Expert Accuracy: Even experts who hold or are pursuing PhDs in the corresponding domains achieve only 65% accuracy on these questions (or 74% when excluding clear mistakes identified in retrospect).

Google-Proof: The questions are “Google-proof,” meaning that even with unrestricted access to the web, highly skilled non-expert validators only reach an accuracy of 34% despite spending over 30 minutes searching for answers.

AI Systems Difficulty: State-of-the-art AI systems, including our strongest GPT-4 based baseline, achieve only 39% accuracy on this challenging dataset.

SimpleBench

https://simple-bench.com/

# Compare online

https://lmarena.ai/

---
title: "（LLM）大语言模型"
subtitle: "(LLM)Large language model"
author: "Tony Duan"

date: "2025-03-18"

categories: 
  - Tool
  - R
  - Python 

  
execute:
  warning: false
  error: false
  eval: false

image: '1734616066-llm-security.webp'
---


(LLM)Large language model

```{r}
library(tidyverse)
library(openxlsx)
library(readxl)
```

```{r}
data001=read_excel('AI model.xlsx')
head(data001)
```

# LLM model performance

## math

### AIME

https://en.wikipedia.org/wiki/American_Invitational_Mathematics_Examination

### MATH-500

## Code

## Codeforces

## LiveCodeBench

## English

### MMLU

Measuring Massive Multitask Language Understanding (MMLU)

https://en.wikipedia.org/wiki/MMLU

## Science

### GPQA-Diamond

Graduate-Level Google-Proof Q&A

Description: GPQA consists of 448 multiple-choice questions meticulously crafted by domain experts in biology, physics, and chemistry. These questions are intentionally designed to be high-quality and extremely difficult.

Expert Accuracy: Even experts who hold or are pursuing PhDs in the corresponding domains achieve only 65% accuracy on these questions (or 74% when excluding clear mistakes identified in retrospect).

Google-Proof: The questions are "Google-proof," meaning that even with unrestricted access to the web, highly skilled non-expert validators only reach an accuracy of 34% despite spending over 30 minutes searching for answers.

AI Systems Difficulty: State-of-the-art AI systems, including our strongest GPT-4 based baseline, achieve only 39% accuracy on this challenging dataset.

# SimpleBench

https://simple-bench.com/

![](images/clipboard-1311795434.png)
# Compare online


https://lmarena.ai/