Home/Models/LLaMA-13B
Meta logo

LLaMA-13B

by Meta · Released Jan 2024

Open Source
30.4
avg score
Rank #178
Compare
Better than 24% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Open Source
Benchmarks
20 tested
Data updated today
About

Tested on 20 benchmarks with 34.9% average. Top scores: Chatbot Arena Elo — Overall (970.9%), TriviaQA (77.9%), LAMBADA (75.2%).

Capabilities
reasoning
9.6
#141 globally
math
11.8
#184 globally
knowledge
43.9
#129 globally
language
25.3
#131 globally
general
25.3
#35 globally
Benchmark Scores
Compare All
Tested on 20 benchmarks · Ranked across 6 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
BBH

BIG-Bench Hard. 23 challenging tasks from BIG-Bench where prior language models fell below average human performance.

17.2
MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

2.0
GSM8K

Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.

20.6
MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

3.1
TriviaQA

Trivia questions sourced from trivia enthusiasts and quiz websites. Tests breadth of general knowledge.

77.9
LAMBADA

Language modeling benchmark testing ability to predict the last word of passages requiring long-range context understanding.

75.2
HellaSwag

Sentence completion requiring commonsense reasoning about physical and social situations. Tests real-world understanding.

72.3
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
llama-13b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Meta logoMetaTBD
Share & Export
Tweet
LLaMA-13B is an open-source text AI model by Meta, released in January 2024. It has an average benchmark score of 30.4.