Back to Models

Llama 2 (70B)

Meta
Released: 2023-07-18
Type: Open Source
Context
4k
Max Out
4.1k
Cutoff
2023-01
Params
70B

The Breakdown

The Llama 2 (70B) represents a significant leap forward in Meta's lineup. Released in 2023-07-18, it targets developers and enterprise use cases with a specific focus on reasoning capabilities over raw conversational speed. While previous iterations in the Open Source category often struggled with complex multi-step instruction following, this model introduces a refined architecture that dramatically improves adherence to system prompts and reduces hallucination rates in technical domains. It competes directly with top-tier frontier models but carves out a distinct niche for workflows where precision and context retention matter more than creative flair. For businesses looking to integrate reliable AI agents, Llama 2 (70B) offers a compelling balance of performance and cost-efficiency.

Overall Score
8.5
/10
Pricing (per 1k tokens)
Input$0
Output$0
Currency: USD

The Good

  • First truly capable open model
  • Commercially usable license
  • Massive community support

The Bad

  • Small context window (4k)
  • Chatty/Repetitive compared to GPT-4

The Verdict

The model that spawned a thousand finetunes.

Performance Benchmarks

mmlu
68.9
human eval
29.9
math
30