Benchmarks

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.

Get smart on it

OpenAI released an updated version of Astra for Law, a specialized configuration of its latest frontier model designed to assist lawyers with legal work. The model performed first on multiple legal benchmarks, including the Harvey LAB-AA test which evaluates whether a model can complete legal assignments across 24 areas of law without making unsupported claims. A key advantage is that Astra for Law achieved its top performance while using significantly fewer output tokens than competing models, which matters for legal teams paying by usage, and it demonstrated a very low rate of hallucinations, errors that could be particularly costly in legal contexts where invented citations can damage a lawyer's credibility. ChatGPT Enterprise customers can now request access to the tool through the Trusted Access Program.

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 →

Google releases Gemini 4 Hydrogen, a lower-cost model said to outscore Argon

Google LLC today released Gemini 4 Hydrogen, a lower-cost model in its Gemini 4 artificial intelligence family said to outscore Google’s frontier Gemini 4 Argon model on an independent intelligence ranking. Measured on the Artificial Analysis Intelligence Index at its default high thinking level, Hydrogen scored 51 to Argon’s 50, according to Google. A fourth […] The post Google releases Gemini 4 Hydrogen, a lower-cost model said to outscore Argon appeared first on SiliconANGLE

Also reported by MarkTechPost and The Decoder

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 →

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.