← Home/

Benchmarks

BigFinanceBench

SWE-Bench Pro

Terminal-Bench

Terminal-Bench-Science

AutomationBench

Toolathlon

OSWorld

BrowseComp

Blueprint-Bench 2
Reconstructs apartment floor plans from sets of interior photos.Anthropic

GeneBench Pro

LifeSciBench

HealthBench Professional

BioMysteryBench

Humanity’s Last Exam

GPQA Diamond

MMMU Pro

gdp.pdf

SEC-Bench Pro

ExploitGym

OpenAI MRCR

GraphWalks

Agents’ Last Exam

GDPval-AA

Hebbia Financial Services Benchmark
Evaluates finance workflows over dense professional documents.Anthropic

DeepSWE

FrontierCode

CursorBench

BenchCAD

Legal Agent Benchmark

DeepSearchQA

FrontierMath

ExploitBench

Internal Research Debugging Evaluation
Diagnoses real bugs from OpenAI research experiments.OpenAI
KernelGen 1P
Writes and optimizes kernels for OpenAI first-party hardware.OpenAI
NanoGPT self-improvement evaluation
Improves language-model training under fixed compute and time.OpenAI

PostTrainBench Lite

ARC-AGI-3