Benchmarks

LoRA adapter lifts Qwen coding success to 65 percent

MarkTechPost: New LoRA Adapter Lifts Qwen3.8 Coding Success From 39% to 65%

Hugging Face’s harness-hub team has released Qwen3.8-27B-pi-adapted, a LoRA adapter for Qwen3.8-27B. It was trained with reinforcement learning to work inside the pi coding agent. The Qwen3.8-27B-pi-adapted LoRA adapter targets one harness instead of general chat. For developers running local coding agents, that is the point. You keep the open base model and swap in a small, harness-specific adapter. TL;DR Size: LoRA rank 32 (alpha 64) on Qwen3.8-27B, a 27B dense hybrid with 262,14

Get smart on it

A LoRA adapter is a small, specialized add-on that modifies how an existing AI model behaves for specific tasks. This new adapter was trained using reinforcement learning to optimize a base model specifically for a coding agent, raising its success rate on a hard coding benchmark from 39.2% to 64.7%. The key advantage is that it achieves accuracy comparable to the base model running in a computationally expensive "thinking mode" while using about 4.5 times fewer tokens, making it more efficient for developers running local coding agents. The adapter can be deployed through several methods including specialized software frameworks, allowing multiple adapters to run on the same base model simultaneously.

Read next
The biggest AI stories, once a day

One short email a day with the stories that matter. Free. Unsubscribe with one click.

Relevant courses

Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.

Browse AI courses on Maven
Related news
BenchmarksOpen story →

MLPerf Training v6.1: Bigger Clusters, Broader Hardware, and the Rise of Software-Driven Gains

The round at a glance MLPerf® Training v6.1 expands the benchmark suite and features even larger systems from our members. Two benchmarks join the suite: Qwen3.5-397B GRPO for agentic reinforcement learning, and DLRMv4-HSTU, a generative recommender. Google’s Ironwood and NVIDIA’s Rubin make their debut as Available systems. The largest jobs reached 10,240 GPUs (NVIDIA on GB300 and Azure on GB200, both training DeepSeek-V3) [1, 2], multi-node systems rose to 76% of the total, and the hardwar

BenchmarksOpen story →

MLCommons Releases MLPerf Training v6.1 Results, Spotlighting Recent Advances in AI Training

Today, MLCommons® announced new results for the MLPerf® Training v6.1 benchmark suite. The two new benchmarks added in this round, and the submissions received, demonstrate the impact of recent architectural advances in AI training systems and the increasing diversity of the hardware used to train them. “We’ve reached an exciting new threshold for the MLPerf Training benchmark suite, with a higher level of participation in this round, the representation of both established and emerging hardw

Also reported by NVIDIA Blog

BenchmarksOpen story →

How good are Fable 5.2 and GPT-6.2 Astra at real work?

We tested Fable 5.2, GPT-6.2 Astra, and four other models on real Epoch work tasks. None met our employee standard, including the two that top our ECI.

BenchmarksOpen story →

Astra for Law leads in legal intelligence

Astra for Law ranked first in a launch evaluation spanning 24 areas of law. Every ChatGPT Enterprise customer can now request access.

BenchmarksOpen story →

Liquid AI Releases d1.2 and d1.2-ultra: Omnimodal Decision Models That Top the AA Decision Index

Liquid AI just released d1.2 and d1.2-ultra. A decision model does not write text. It returns calibrated probabilities over a fixed set of answers. The Liquid AI d1.2 decision model family now accepts text, images and audio. It also adds 5 new answer types. d1.2-ultra scores 75 on the Artificial Analysis Decision Index v2.1, the top score among decision models on the index. You can check the deployment options and specs here through our GPULeaderboard.com chrome extension. TL;DR Size: Pa

BenchmarksOpen story →

A step toward defining the Standard Model on a lattice

Explore a candidate nonperturbative lattice definition of the Standard Model and how GPT-6 Astra helped turn the idea into a detailed proof.