Tasks in the ATLAS finance benchmark require constructing financial spreadsheets containing over 4,000 active cells and 2,600 live formulas

Overview Debates Related claims Topics

Handshake AI developed the VIALS benchmark to evaluate the capability of AI models to interpret life science laboratory assays

The VIALS benchmark evaluates model interpretation on tasks including plasmid DNA sequence percentages, molecular hydrogen bond counts, and medical histology images

Handshake AI developed the ATLAS finance benchmark, comprising 100 tasks evaluated across 13 simulated financial environments

Frontier models including MiniMax, GLM, and Grok score below a 20 percent pass rate on the VIALS benchmark

Autonomous AI agents provided with scientific Python libraries like SciPy and OpenCV achieve under 60 percent accuracy on VIALS benchmark tasks

Frontier AI models achieve a pass rate of under 20 percent on the ATLAS finance benchmark

Out of the box, frontier AI models achieve pass rates of 50 percent or worse across the VIALS life science benchmark

The SemiAnalysis GDPX benchmark evaluates artificial intelligence models on economically valuable tasks such as chip design, finance, and biology

In the DrivingBench benchmark, GPT-6 Astra reached halfway on its first attempt and completed the entire physical Toyota Corolla driving course on its second attempt

In the DrivingBench benchmark, Grok 4.6 completed a maximum of 11% of a physical Toyota Corolla driving course across three attempts

In the DrivingBench benchmark, Claude Fable 5.1 completed half of a physical Toyota Corolla driving course on its third attempt

As of October 2026, OpenAI is developing an investment banking evaluation benchmark designed to assess the automation of junior analyst workflows

On the GDPVAL AA benchmark for agentic white-collar work, Kimi K3.1 ranked behind Opus 5.5 and ahead of Fable 5.1

DeepSeek V41 Flash and GLM 5.3 scored in the low 40s on the Terminalbench 4.0 benchmark

On the Terminalbench 4.0 benchmark for agentic coding, Kimi K3.1 scored less than one point behind Opus 5.5

On the Terminalbench 4.0 benchmark, Kimi K3.1 scored approximately seven points ahead of GPT6 Astra and Fable 5.1

OpenAI released the HealthBench evaluation benchmark in May 2025 to evaluate AI performance across layperson and clinician communication personas

OpenAI released GPT-6 Luna, which scored higher on the HealthBench Professional clinical benchmark than GPT-5.6 Sol while costing 34 times less

Gemini 4 Argon achieved state-of-the-art benchmark scores on the VALS Index Automation Bench, VALS Finance Agent, and Harvey Legal Agent benchmark

On the Terminal Bench 4.0 benchmark, Gemini 4 Argon scored nine points lower than leading model Opus 5.5