Llama 2 Chat 70B

Llama 2 Chat 70B

Meta · Released Jul 18, 2023
Intelligence #659 / 715
12.0 our score
AA Index #395 / 428
2.6 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Llama 2 Chat 70B is Meta's larger 2023 conversational model, offering more capacity than the 7B and 13B variants in this batch. Its general benchmark results remain limited by current standards, although the larger model supports more coherent responses and broader knowledge handling. The supplied data does not show modern tool use, agentic performance, context capacity, or current pricing advantages.

The model can handle basic customer support drafts, summarisation, classification, and internal experimentation when a team controls prompts and validates outputs. It is not appropriate for complex reasoning, reliable coding agents, or high-stakes client copy without substantial review. Consider it only for legacy systems or self-hosted workloads where infrastructure control is the primary requirement.

Assessed August 9, 2026

Editorial notes

Llama 2 Chat 70B provides better conversational and factual performance than smaller Llama 2 variants, but its dated benchmark profile and limited coding results leave stronger options for production content and automation.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Llama 2 Chat 70B provides better conversational and factual performance than smaller Llama 2 variants, but its dated benchmark profile and limited coding results leave stronger options for production content and automation.

#659 of 715 overall Down 15 this week

Benchmark scores

GPQA Diamond 32.7%
HLE 5%
MMLU Pro 40.6%
MATH 500 32.3%
LiveCodeBench 9.8%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

2.6 Intelligence Index

How Llama 2 Chat 70B compares

Llama 2 Chat 70B ranks #395 of 428 AI models we track for overall intelligence. Llama 2 Chat 70B is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 8% of models #659
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Llama 2 Chat 70B $0.00 in $0.00 out
OpenAI: GPT-5.6 Sol $2.00 in $10.00 out
Claude Opus 5 $5.00 in $25.00 out
SpaceXAI: Grok 4.6 $2.00 in $6.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens
Llama 2 Chat 70B 0

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence1.1Technical0Value0Content4
Performance profile

Strongest on content. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Llama 2 Chat 70B

How much does Llama 2 Chat 70B cost?

Llama 2 Chat 70B is currently available for free via OpenRouter.

Who created Llama 2 Chat 70B?

Llama 2 Chat 70B is developed by Meta and was released on July 18, 2023.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.