跳轉到主要內容

ERNIE 4.5 300B A47B

BaiduProprietary

描述

ERNIE 4.5 is an enhanced version of ERNIE 4.0 with improved reasoning capabilities, better instruction following, and stronger performance across multiple domains including mathematics, coding, and creative writing. Features advanced knowledge integration, multilingual support, and optimized thinking capabilities. This 21B parameter model uses A3B quantization for efficient inference.

發布日期
2025-06-30
參數規模
21.0B
上下文長度
123K
支援模態
image, text

能力雷達圖

29
general
43
coding
55
reasoning
48
science
51
agents
80
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜402
22.0
AA
通用能力榜413
30.0
AA
科學能力265
47.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)74.0%自報

Factuality

SimpleQA1.8%自報

Finance

MMLU41.9%自報
MMLU-Pro16.0%自報

General

ARC-E60.7%自報
PIQA55.2%自報
MMLU-Redux43.2%自報
C-Eval40.7%自報
ARC-C40.6%自報
MBPP+40.2%自報
CMMLU39.8%自報
AGIEval28.5%自報

Language

Winogrande51.3%自報
CLUEWSC48.6%自報
BBH30.4%自報

Math

DROP28.6%自報
GSM8k25.2%自報
MATH12.4%自報

Reasoning

HellaSwagAI2 (2019)33.0%自報
HumanEval+25.0%自報

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
41.3
Intelligence Index(Artificial Analysis)
8.9
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Aime(MAA (Mathematical Association of America))
0.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.5
Aime 25(MAA (Mathematical Association of America))
0.4
Ifbench(Google Research (2023))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.3
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1
Lcr(Artificial Analysis)
0.0
Hle(Center for AI Safety + Scale AI (2025))
0.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Biology
70
Chemistry
70
Physics
60
Language
40
Reasoning
40
General
40
Legal
30
Math
30
Finance
30
Healthcare
30
Factuality
0

定價

輸入價格$0.28 / 1M tokens
輸出價格$1.1 / 1M tokens
混合價格(3:1)$0.485 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

5 個供應商

最便宜: Baidu最貴: Kilo Gateway
供應商輸入輸出
1Baidu主要
$0.28
$1.1
2OpenRouter
$0.42
$1.25
3Jiekou.AI
$0.42
$1.25
4NovitaAI
$0.42
$1.25
5Kilo Gateway
$0.42
$1.25

比較該模型在不同 API 供應商之間的定價。

外部連結