AIbase
EN
Home
AI Models Finder
Llama 3.1 Tulu3 405B
L

Llama 3.1 Tulu3 405B

基於 Llama 3.1 架構的大規模 Tulu3 模型，擁有 405B 參數規模。Tulu 系列以其優秀的指令調優而聞名，這個版本在保持 Llama 3.1 強大基礎能力的同時，透過 Tulu 的優化技術提升了指令遵循和對話能力。適合需要最高級 AI 能力的研究機構和大型企業，能夠處理最複雜的自然語言任務。
Intelligence(Relatively Weak)
Speed(Slow)
Input Supported Modalities
No
Is Reasoning Model
128,000
Context Window
128,000
Maximum Output Tokens
2023-12-01
Knowledge Cutoff
Go Compare

Pricing

￥6.48 /M tokens
Input
￥6.48 /M tokens
Output
- /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Llama 3.1 Tulu3 405B
￥0.9

Basic Parameters

Llama 3.1 Tulu3 405BTechnical Parameters
Parameter Count
405,000.0M
Context Length
128.00k tokens
Training Data Cutoff
2023-12-01
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
100
Release Date
2025-01-30
Response Speed
0 tokens/s

Benchmark Scores

Below is the performance of Llama 3.1 Tulu3 405B in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
39.92
Large Language Model Intelligence Level
Coding Index
29.65
Indicator of AI model performance on coding tasks
Math Index
45.57
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
71.6
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
51.6
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
3.5
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
29.1
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
30.2
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
89
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
77.8
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
13.3
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase