AIBase
Home
AI NEWS
AI Tools
GEO & AEO
MCP
AI Models
EN

AI News

View More

AI 学霸遭遇重创!GPT-4o 专家考试仅得 2.7 分

《自然》杂志报道,GPT-4o 在“人类终极考试”中仅得 2.7 分(满分 100),表现最佳 AI 模型也仅 8 分。这一结果引发对 AI 真实能力的质疑。传统测试难以反映真实水平,主要因“基准饱和”问题。

15.8k 2 hours ago
AI 学霸遭遇重创!GPT-4o 专家考试仅得 2.7 分

Models

View More

Claude 3 Opus

Anthropic

Claude 3 Opus

$105

Input tokens/M

$525

Output tokens/M

200

Context Length

qwen-image-edit

Alibaba

qwen-image-edit

-

Input tokens/M

-

Output tokens/M

-

Context Length

Qwen3-235B-A22B-Instruct-2507

Alibaba

Qwen3-235B-A22B-Instruct-2507

$2

Input tokens/M

-

Output tokens/M

64

Context Length

GLM-4.5-X

Chatglm

GLM-4.5-X

$8

Input tokens/M

$16

Output tokens/M

128

Context Length

o3

Openai

o3

$14

Input tokens/M

$56

Output tokens/M

200

Context Length

ERNIE-4.5-VL-424B-A47B-Paddle

Baidu

ERNIE-4.5-VL-424B-A47B-Paddle

-

Input tokens/M

-

Output tokens/M

-

Context Length

Yi-9B-200K

01-ai

Yi-9B-200K

-

Input tokens/M

-

Output tokens/M

200

Context Length

GLM-4

Chatglm

GLM-4

$100

Input tokens/M

$100

Output tokens/M

128

Context Length

Gemini 1.0 Pro

Google

Gemini 1.0 Pro

$3.5

Input tokens/M

$10.5

Output tokens/M

32

Context Length

Yi-6B-Chat

01-ai

Yi-6B-Chat

-

Input tokens/M

-

Output tokens/M

4

Context Length

Baichuan-7B

Baichuan

Baichuan-7B

-

Input tokens/M

-

Output tokens/M

4

Context Length

ERNIE-3.0

Baidu

ERNIE-3.0

-

Input tokens/M

-

Output tokens/M

4

Context Length

ERNIE-1.0

Baidu

ERNIE-1.0

-

Input tokens/M

-

Output tokens/M

4

Context Length

AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAI MarketingLLM LeaderboardAI Ranking
© 2026AIBase
Business CooperationSite Map