L2 · ANALYST

LLM as Analyst

Research agents with stronger analysis, modeling, and experiment-execution abilities — they plan and reason across steps.

Listed alphabetically by intended research role. A level is not a quality score or a verified capability rating; benchmark entries describe evaluation resources for that role.

TOOLS IN THIS LEVEL

14 indexed

BioAgents

Open-source

Biology research agents

Research Agents & AI Scientists

BLADE

Open-source

Benchmark for agents doing scientific data analysis

Research Agents & AI Scientists

Coscientist

Open-source

Chemistry-focused co-scientist

Research Agents & AI Scientists

DiscoveryWorld

Open-source

Scientific discovery benchmark world

Research Agents & AI Scientists

DrugAgent

Free

Multi-agent programming for AI-aided drug discovery

Research Agents & AI Scientists

DS-Agent

Open-source

Data science research agent

Research Agents & AI Scientists

DSBench

Open-source

Data science agent benchmark

Research Agents & AI Scientists

LLM-SR

Open-source

LLM for symbolic regression

Research Agents & AI Scientists

LLM-SRBench

Open-source

Benchmark for LLM symbolic regression

Research Agents & AI Scientists

MLAgentBench

Open-source

ML research agent benchmark

Research Agents & AI Scientists

MLE-bench

Open-source

ML engineer benchmark (OpenAI)

Research Agents & AI Scientists

MLR-Copilot

Open-source

ML research copilot

Research Agents & AI Scientists

NewtonBench

Open-source

Physics discovery benchmark

Research Agents & AI Scientists

ProtAgents

Free

Protein research agents

Research Agents & AI Scientists

WHAT DO THE LEVELS MEAN?

L0 · Reference — Reference Resources: Curated lists, awesome-repos, and initiatives that support AI-in-research workflows — starting points, not end-products.
L1 · Tool — LLM as Tool: AI tools that augment a single researcher task — literature search, writing, reviewing, figure generation, content transformation.
L2 · Analyst — LLM as Analyst: Research agents with stronger analysis, modeling, and experiment-execution abilities — they plan and reason across steps.
L3 · Scientist — LLM as Scientist: Systems intended to connect hypothesis generation, experiments, analysis, and paper drafting. Their autonomy and evidence vary by project and research domain.