LLM Reference

Orca 2 13B

Released
2023-11-21
Last refreshed
2026-05-19
Status
Researched 105d ago
Open weightsCommercial use: non-commercialCodingClassification

Orca 2 13B is worth evaluating for coding and classification when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding and classification
  • Workloads that can use a 4k 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
Orca 2
Released
2023-11-21
Context
4k
Parameters
13B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Microsoft Research(needs verification)Commercial use: non-commercial
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Advancing the state-of-the-art in AI and computing.

Redmond, Washington, United States
Founded 1991
Website
Pricing
Output / 1M
$0.940
Input / 1M
$0.810

Cheapest of 1 route · Microsoft Foundry

About

Orca 2 13B, developed by Microsoft, is a large language model designed primarily for research purposes. It is a fine-tuned version of the LLaMA-2 base model, focusing on enhanced reasoning capabilities in smaller language models. This is achieved through training on a synthetic dataset specifically created to improve reasoning skills. Orca 2 13B excels in tasks such as reading comprehension, math problem-solving, and text summarization. However, it is not optimized for chat applications and requires fine-tuning for specific tasks.

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

Coding

Q/$ C

1 relevant benchmark in the decision map.

Classification

Q/$ C

1 relevant benchmark in the decision map.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

Benchmark scores(2)

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
HumanEval35.2pass@1Observed 2026-03-06Source
Massive Multitask Language Understanding70.85-shotObserved 2026-03-06Source

Migration checks

No linked migration route is available for this model yet.