NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Llama 2 7b Chat Hf
Meta logo

Llama 2 7b Chat Hf

by Meta · Released Jul 2023

Open Source
25.4
avg score
Rank #264
Compare
Better than 15% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text-generation
License
Open Source
Benchmarks
11 tested
Data as of
About

Meta-llama text generation model. 432K downloads on HuggingFace.

Tested on 11 benchmarks · BenchGecko score 25.4. Top scores: JSQuAD (83.0%), JCommonsenseQA (52.6%), IFEval (39.9%).

Capabilities
reasoning
3.3
#214 globally
math
2.0
#272 globally
knowledge
4.0
#296 globally
language
47.1
#126 globally
general
4.5
#209 globally
Benchmark Scores
Compare All
Tested on 11 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR

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

3.3·
mathCompare math →
MATH Level 5

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

2.0·
knowledgeCompare knowledge →
MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

7.6·
GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

0.5·
Quick compare:Mistral AI logovs Mistral Medium 3.5Alibaba Qwen logovs CodeQwen1.5-7BCohere logovs Command R (08-2024)
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
Mistral AI logo
Mistral Medium 3.5
Mistral AI
25.0$1.50/1M
Alibaba Qwen logo
CodeQwen1.5-7B
Alibaba Qwen
24.6n/a
Cohere logo
Command R (08-2024)
Cohere
26.2$0.15/1M
Links
Info
MetaPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Meta
Source Code
GitHubHugging Face
BenchGecko API
meta-llama-llama-2-7b-chat-hf
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedJul 2023
  • LicenseOpen Source
  • StatusActive
Available On
Meta logoMetan/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Mistral AI logoMistral Medium 3.5
25.0
Alibaba Qwen logoCodeQwen1.5-7B
24.6
Cohere logoCommand R (08-2024)
26.2
Anthropic logoClaude 3.5 Haiku
24.5
Llama 2 7b Chat Hf is an open-source text-generation AI model by Meta, released in July 2023. It has an average benchmark score of 25.4.

Related Models

Mistral Medium 3.5 · Mistral AICodeQwen1.5-7B · Alibaba QwenCommand R (08-2024) · CohereClaude 3.5 Haiku · AnthropicClaude 3 Haiku · Anthropic

Benchmarks

JSQuADJCommonsenseQAIFEvalLLM-JP — OverallJNLI

Related Pages

Meta · ProviderMeta · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Llama 2 7b Chat Hf by Meta. BenchGecko score 25.4, rank 264 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 7b Chat Hf · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/meta-llama-llama-2-7b-chat-hf

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