Intern Science

company

https://discovery-home.intern-ai.org.cn/home

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

BoZhang updated a model about 3 hours ago

InternScience/Agents-A1

sY713 submitted a paper about 4 hours ago

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

sY713 updated a model about 21 hours ago

InternScience/Agents-A1

View all activity

Papers

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

View all Papers

InternScience 's collections 5

InternAgent

InternAgent aims to facilitate AI+X innovative research across diverse scientific domains

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Paper • 2602.08990 • Published Feb 9 • 79
BoZhang/OmniCaptioner

8B • Updated Apr 10, 2025 • 7 • 20
InternScience/StructTable-base

Image-to-Text • 0.3B • Updated Dec 6, 2025 • 24 • 11
InternScience/MME-Reasoning

Preview • Updated Jun 13, 2025 • 181 • 9

SGI-Bench

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Running

Agents

9

SGI-Bench Leaderboard

🥇

9

Scientific General Intelligence of LLMs/vLLMs
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published Dec 18, 2025 • 121
InternScience/SGI-DeepResearch

Viewer • Updated 28 days ago • 318 • 253 • 9
InternScience/SGI-IdeaGeneration

Viewer • Updated 28 days ago • 315 • 289 • 4

SFE

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Paper • 2506.10521 • Published Jun 12, 2025 • 75
InternScience/SFE

Viewer • Updated Dec 24, 2025 • 1.66k • 1.09k • 19
InternScience/SFE-train

Preview • Updated Oct 10, 2025 • 77 • 1

ResearchClawBench

ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published May 28 • 98
InternScience/ResearchClawBench

Benchmark • Updated 6 days ago • 57 • 3.47k • 8
Running

3

ResearchHarness

🚀

3

Lightweight harness for tool-using LLM agents.
Running

Agents

1

ResearchClawBench Task Submission

📦

1

Submit and validate a ResearchClawBench task ZIP

SciEval-Bench

Paused

Agents

4

SciEval Leaderboard

🥇

4

Open, science-focus leaderboards benchmarking LLMs and VLMs
InternScience/SciEval

Preview • Updated Dec 4, 2025 • 203 • 1
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

Paper • 2512.22334 • Published Dec 26, 2025 • 37