Benchmarks

Hebbia sees improvements in financial research with GPT-6 Astra

Hebbia tested GPT-6 Astra for financial research. Its prerelease evaluations found gains in source coverage, citation relevance, and presentation quality.

Get smart on it

A financial research startup tested a new AI model to improve how bankers analyze acquisition deals by finding relevant source documents and creating presentation slides. The model scored higher than alternatives on two key measures: citing the right types of sources with relevant excerpts and meeting presentation formatting requirements that make outputs look professionally made rather than AI-generated. This matters because bankers base million-dollar decisions on AI outputs, so accurate citations and proper formatting reduce time spent verifying and reformatting while increasing confidence in the results.

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 →

AI claimed a solution to the 167 year-old Riemann Hypothesis, and a human did, too

Mathematicians are having their minds blown by the latest AI-driven result—and there's a competing human solution, too.

Also reported by SiliconANGLE

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 →

Can AI help scientists identify promising drug candidates?

MedChemBench evaluates how well AI models interpret molecular structures, reason from experimental evidence, and select compounds in early drug discovery.

BenchmarksOpen story →

Meta FAIR Self-Improving Memory Hits 56.0 on Continual Learning Bench

Meta FAIR has introduced Self-Improving Memory, a method for AI agents that manage their own memory. The model first discovers its own memory instructions. It then trains those skills into its weights. Co-authors include researchers from the University of Washington and Johns Hopkins University. TL;DR Method: The base is Kimi-K2.6, a 1T-parameter MoE with 32B active and 256K context. Distillation adds a LoRA adapter (rank 64) on attention projections. Runs on: Training hardware is no

BenchmarksOpen story →

Research acceleration: The jagged frontier

OpenAI measures how coding agents are accelerating AI research, where their performance remains uneven, and what this signals about recursive self-improvement.

BenchmarksOpen story →

Agentic inference capacity grew 4.6× in a year, versus 2.6× for compute capacity

Our Inference Performance Index and chip sales data show agentic inference capacity grew nearly twice as much as 8-bit compute.