Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

It's a plan
It's a plan
Busbar
Busbar
Omnigraph
Omnigraph
Trina AX
Trina AX
Bifrost
Bifrost
OfinTech Desk
OfinTech Desk

harbor-framework/terminal-bench-science

Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

#LLM evaluation
Visit GitHub
Python
956
575
15 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Trina AX

A self-hosted team AI workspace for company files, with per-person folder permissions

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Momentum

How fast harbor-framework/terminal-bench-science is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 23 – Nov 22, 2026

Stars +340 in 61 days

051015
14

Forks +224 in 61 days

051015
14

Merged PRs 141 in 61 days

0204060
43

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 23Oct 1Oct 9Oct 17Oct 25Nov 2Nov 10Nov 18
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Wed, Sep 23, 2026+8+12
Thu, Sep 24, 2026+4+20
Fri, Sep 25, 2026+2+00
Sat, Sep 26, 2026+4+00
Sun, Sep 27, 2026+6+60
Mon, Sep 28, 2026+5+70
Tue, Sep 29, 2026+7+70
Wed, Sep 30, 2026+2+50
Thu, Oct 1, 2026+9+50
Fri, Oct 2, 2026+6+40
Sat, Oct 3, 2026+1+100
Sun, Oct 4, 2026+2+120
Mon, Oct 5, 2026+4+140
Tue, Oct 6, 2026+1+120
Wed, Oct 7, 2026+2+70
Thu, Oct 8, 2026+8+60
Fri, Oct 9, 2026+8+10
Sat, Oct 10, 2026+5+40
Sun, Oct 11, 2026+3+21
Mon, Oct 12, 2026+4+51
Tue, Oct 13, 2026+5+31
Wed, Oct 14, 2026+4+50
Thu, Oct 15, 2026+3+30
Fri, Oct 16, 2026+5+40
Sat, Oct 17, 2026+6+40
Sun, Oct 18, 2026+4+20
Mon, Oct 19, 2026+5+20
Tue, Oct 20, 2026+6+20
Wed, Oct 21, 2026+3+20
Thu, Oct 22, 2026+4+10
Fri, Oct 23, 2026+3+30
Sat, Oct 24, 2026+2+10
Sun, Oct 25, 2026+4+21
Mon, Oct 26, 2026+6+20
Tue, Oct 27, 2026+3+20
Wed, Oct 28, 2026+8+50
Thu, Oct 29, 2026+6+40
Fri, Oct 30, 2026+8+31
Sat, Oct 31, 2026+4+21
Sun, Nov 1, 2026+5+34
Mon, Nov 2, 2026+8+22
Tue, Nov 3, 2026+8+13
Wed, Nov 4, 2026+4+23
Thu, Nov 5, 2026+3+33
Fri, Nov 6, 2026+7+51
Sat, Nov 7, 2026+11+13
Sun, Nov 8, 2026+11+10
Mon, Nov 9, 2026+9+22
Tue, Nov 10, 2026+6+44
Wed, Nov 11, 2026+14+419
Thu, Nov 12, 2026+14+522
Fri, Nov 13, 2026+8+243
Sat, Nov 14, 2026+4+71
Sun, Nov 15, 2026+3+20
Mon, Nov 16, 2026+5+20
Tue, Nov 17, 2026+13+421
Wed, Nov 18, 2026+13+32
Thu, Nov 19, 2026+6+50
Fri, Nov 20, 2026+5+20
Sat, Nov 21, 2026+3+20
Sun, Nov 22, 2026+0+00
Total+340+224141
  • 1#1 on the list
  • 7Rank that day
  • Not trending
  • Mentions and achievements

    Where people are talking about harbor-framework/terminal-bench-science, and every badge it has earned
    1. Sep 251 post
      • On AA's new Terminal-Bench-Science board, only two models clear half the tasks: GPT-6 Astra (max) at 63%, Claude Opus 5.5 (xhigh) at 62%. Best open-weights entry: GLM-5.3 (max) at 10%. Third-party…

        Read full on X, posted by @jimmy_longbow_

        @jimmy_longbow_ · x.com

    2. 29 days earlier
    3. Aug 271 post
      • Terminal-Bench-Science was made possible by our research partners @StanfordAILab, @stanfordnlp, @StanfordHAI, @2077AI, @MLFoundations, @AllenInstitute, @allen_ai, and our compute sponsors…

        Read full on X, posted by @StevenDillmann

        @StevenDillmann · x.com

    4. 23 days earlier
    5. Aug 41 post
      • I submitted a science task proposal to Terminal Bench science today FYI their deadline for submitting the PR (not the merge) is Aug 17!

        Read full on X, posted by @sgjarmak

        @sgjarmak · x.com

    6. Aug 21 post
      • Most AI benchmarks test toys. This one tests whether an AI can actually do science. Terminal-Bench Science (TB-Science) is an open benchmark for AI agents that run real scientific workflows inside…

        Read full on X, posted by @itsharmanjot

        @itsharmanjot · x.com

    7. 2 months earlier
    8. May 201 post
      • What a task looks like — real workflows from scientific domain experts: - Reconstructing MRI brain maps - Virtual drug screening - Reconstructing ice crystal disorder over time Scientifically…

        Read full on X, posted by @StevenDillmann

        @StevenDillmann · x.com

    You might also like

    Repositories close to harbor-framework/terminal-bench-science
    FeaturedAdvertise to 180K+ monthly visitors
    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    Trina AX

    A self-hosted team AI workspace for company files, with per-person folder permissions

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Busbar

    Control what AI can do before it acts

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    InternScience/ResearchClawBench

    Jupyter Notebook

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

    28230

    Gen-Verse/Science-Last-Exam

    Python

    Science's Last Exam

    272

    EdisonScientific/labbench2

    Python

    labbench2

    7021

    prometheus-eval/into-the-unknown

    Python

    Official code repository for "Into the Unknown: Benchmarking AI agents on open scientific research problems"

    324

    boltzmannlabs/agent-scientist

    Python
    41

    CherYou/AutoResearchBench

    Python

    Official Repo: AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

    763

    SakanaAI/AI-Scientist-v3

    Python

    The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery

    73997

    EvoScientist/EvoScientist

    Python

    🔬 Harness Vibe Research with Self-evolving AI Scientists

    5.1k392

    gudehhh666/Awesome_Scientific_Agent

    Python

    Awesome Scientific Agent

    839