NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Llama 2-13B
Meta logo

Llama 2-13B

by Meta · Released Jan 2024

Open Source
36.4
avg score
Rank #214
Compare
Better than 31% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Open Source
Benchmarks
17 tested
Data as of
About

Tested on 17 benchmarks · BenchGecko score 36.4. Top scores: TriviaQA (79.6%), LAMBADA (76.5%), HellaSwag (74.3%).

Capabilities
reasoning
44.3
#92 globally
math
13.4
#248 globally
knowledge
42.6
#182 globally
general
3.7
#211 globally
Benchmark Scores
Compare All
Tested on 17 benchmarks · Ranked across 4 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
BBH

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

44.3·
mathCompare math →
GSM8K

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

36.9·
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

3.3·
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

0.0·
knowledgeCompare knowledge →
TriviaQA

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

79.6·
LAMBADA

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

76.5·
HellaSwag

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

74.3·
Quick compare:Alibaba Qwen logovs Qwen3 8BMeta logovs Llama 3.2 90BAlibaba Qwen logovs Qwen3.5-Flash
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Meta Llama 2
Jul 2023
25.4
n/an/actx11 benchmarks
Jul 2023
21.5-3.9
n/an/actx11 benchmarks
Jan 2024
36.4+14.9
n/an/actx17 benchmarks
See the full Llama 2 family →
Similar Models
Alibaba Qwen logo
Qwen3 8B
Alibaba Qwen
36.3$0.12/1M
Meta logo
Llama 3.2 90B
Meta
36.3n/a
Alibaba Qwen logo
Qwen3.5-Flash
Alibaba Qwen
36.5$0.07/1M
Links
Info
MetaPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Meta
Source Code
GitHubHugging Face
BenchGecko API
llama-2-13b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Meta logoMetan/a
Categories
reasoningmathknowledgegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba Qwen logoQwen3 8B
36.3
Meta logoLlama 3.2 90B
36.3
Alibaba Qwen logoQwen3.5-Flash
36.5
Google DeepMind logoGemini 1.5 Pro (May 2024)
36.3
Llama 2-13B is an open-source text AI model by Meta, released in January 2024. It has an average benchmark score of 36.4.

Related Models

Qwen3 8B · Alibaba QwenLlama 3.2 90B · MetaQwen3.5-Flash · Alibaba QwenGemini 1.5 Pro (May 2024) · Google DeepMindQwen2.5-Max · Alibaba Qwen

Benchmarks

TriviaQALAMBADAHellaSwagPIQAARC AI2

Related Pages

Meta · ProviderMeta · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Llama 2-13B by Meta. BenchGecko score 36.4, rank 214 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

Llama 2-13B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/llama-2-13b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP