EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge

TL;DR

EdgeRunner 20B is a fine-tuned military-focused language model that matches or exceeds GPT-5 performance on military tasks, demonstrating the viability of small, edge-deployable models for sensitive military applications.

Contribution

The paper introduces EdgeRunner 20B, a new military-optimized language model trained on specialized data, with extensive evaluation showing its competitive performance and deployment advantages.

Findings

EdgeRunner 20B matches or exceeds GPT-5 on military tasks.

No significant performance regression on general benchmarks.

Small models are suitable for secure, edge deployment in military contexts.

Abstract

We present EdgeRunner 20B, a fine-tuned version of gpt-oss-20b optimized for military tasks. EdgeRunner 20B was trained on 1.6M high-quality records curated from military documentation and websites. We also present four new tests sets: (a) combat arms, (b) combat medic, (c) cyber operations, and (d) mil-bench-5k (general military knowledge). On these military test sets, EdgeRunner 20B matches or exceeds GPT-5 task performance with 95%+ statistical significance, except for the high reasoning setting on the combat medic test set and the low reasoning setting on the mil-bench-5k test set. Versus gpt-oss-20b, there is no statistically-significant regression on general-purpose benchmarks like ARC-C, GPQA Diamond, GSM8k, IFEval, MMLU Pro, or TruthfulQA, except for GSM8k in the low reasoning setting. We also present analyses on hyperparameter settings, cost, and throughput. These findings show that small, locally-hosted models are ideal solutions for data-sensitive operations such as in the military domain, allowing for deployment in air-gapped edge devices.