LLM Reference

Starling LM 7B Beta

Released
2024-02-05
Last refreshed
2026-05-19
Status
Researched 60d ago
Open weightsCommercial use: conditionalCodingClassification

Starling LM 7B Beta is a released coding and classification model with open-weight; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating coding and classification
  • Workloads that can use a 8k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Starling
Released
2024-02-05
Context
8k
Parameters
7B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Llama 2 CommunityCommercial use: conditional
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Open-source AI, complete data control.

Palo Alto, California, United States
Founded 2023
Website
Pricing

No tracked provider token pricing is available yet.

About

Starling LM 7B Beta is an open-source large language model crafted by Nexusflow, leveraging a 7-billion parameter transformer architecture tailored for conversational AI. Fine-tuned with Reinforcement Learning from AI Feedback (RLAIF), it aims to enhance helpfulness and minimize harm. Built on the foundation of the Openchat-3.5-0106 and Mistral-7B-v0.1 models, it utilizes the berkeley-nest/Nectar ranking dataset, Nexusflow/Starling-RM-34B reward model, and Proximal Policy Optimization (PPO) strategy. Achieving an improved MT Bench score of 8.12, its capabilities span engaging conversations, informative responses, and tasks like content and code generation. While it shows strong performance among 7B models, verbose outputs and strict adherence to a provided chat template are notable considerations. Licensed under Apache-2.0 with restrictions against competing with OpenAI, it continues to offer robust functionality within its calibrated framework.

Starling LM 7B Beta is an open-weight model in the Starling family. The structured metadata tracks a 8k-token context window. Headline tracked benchmarks include Google-Proof Q&A 49.7, HellaSwag 89.2, and HumanEval 74.2.

Top use-case fit: coding, agents, and build tasks

Coding

1 relevant benchmark in the decision map.

Classification

2 relevant benchmarks in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Google-Proof Q&A49.7diamondObserved 2026-03-06Source
HellaSwag89.210-shotObserved 2026-03-06Source
HumanEval74.2pass@1Observed 2026-03-06Source
Massive Multitask Language Understanding77.85-shotObserved 2026-03-06Source

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Starling LM 7B Beta?

Starling LM 7B Beta has a context window of 8k tokens.

When was Starling LM 7B Beta released?

Starling LM 7B Beta was released on 2024-02-05.

What benchmarks has Starling LM 7B Beta been tested on?

Starling LM 7B Beta has been evaluated on 4 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding.