LLM Reference

Smaug 72B

Released
2023-12-09
Last refreshed
2026-05-19
Status
Researched 16d ago

Smaug 72B is worth evaluating for general LLM work when its provider route and context window match the workload.

Use it for

  • Teams evaluating general LLM work
  • Workloads that can use a 32k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Smaug
Released
2023-12-09
Context
32k
Parameters
72B
Architecture
Decoder Only
Specialization
general
Training
finetuned
Created by

AI Research and Cloud Services.

San Francisco, California, United States
Founded 2019
Website
Pricing
Output / 1M
$2.00
Input / 1M
$1.00

Cheapest of 1 route · Microsoft Foundry

About

Smaug 72B is a large language model (LLM) developed by Abacus AI, distinguished as the first open-source model to exceed an average score of 80% on the Hugging Face Open LLM Leaderboard. It excels in various tasks, outperforming even some proprietary models like GPT-3.5 in specific benchmarks. The model is based on the Qwen-72B and fine-tuned using a novel DPO-Positive (DPOP) technique, leveraging datasets such as ARC, HellaSwag, and MetaMath. Its capabilities include question answering, text translation, and poem generation, with notable performance in reasoning and math tasks. Despite its strengths, Smaug 72B faces limitations such as dataset contamination and challenges in complex contextual understanding. Its open-source nature allows for community-based enhancements and it supports a 32k context length for processing longer inputs.

Smaug 72B is a model in the Smaug family. The structured metadata tracks a 32k-token context window. This page tracks provider routes through Microsoft Foundry, with the cheapest tracked route listed at $1 input and $2 output per 1M tokens. No headline benchmark score is tracked for Smaug 72B yet.

Top use-case fit

No primary decision-task fit is mapped for this model yet.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Microsoft Foundry$1.00$2.00
Provisioned

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Rankings & picks(4)