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

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Busbar
Busbar
Bifrost
Bifrost
AxiomCode
AxiomCode

MirroS-Lab/HarnessEval-W

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

#LLM evaluation
Visit GitHub
Python
308
11
3 contributors
website
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

AxiomCode

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Momentum

How fast MirroS-Lab/HarnessEval-W 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

Aug 20 – Oct 19, 2026

Stars +104 in 61 days

0102030
26

Forks +7 in 61 days

0123
3

Merged PRs 0 in 61 days

01

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

Not in the Trendshift top 25 in this period

Aug 20Aug 28Sep 5Sep 13Sep 21Sep 29Oct 7Oct 15
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
Thu, Aug 20, 2026+26+30
Fri, Aug 21, 2026+11+00
Sat, Aug 22, 2026+5+00
Sun, Aug 23, 2026+5+00
Mon, Aug 24, 2026+8+00
Tue, Aug 25, 2026+6+00
Wed, Aug 26, 2026+1+10
Thu, Aug 27, 2026+1+00
Fri, Aug 28, 2026+1+10
Sat, Aug 29, 2026+3+10
Sun, Aug 30, 2026+4+00
Mon, Aug 31, 2026+3+00
Tue, Sep 1, 2026+5+00
Wed, Sep 2, 2026+3+00
Thu, Sep 3, 2026+0+00
Fri, Sep 4, 2026+2+10
Sat, Sep 5, 2026+0+00
Sun, Sep 6, 2026+1+00
Mon, Sep 7, 2026+1+00
Tue, Sep 8, 2026+3+00
Wed, Sep 9, 2026+1+00
Thu, Sep 10, 2026+2+00
Fri, Sep 11, 2026+0+00
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+0+00
Tue, Sep 15, 2026+0+00
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+1+00
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+1+00
Tue, Sep 22, 2026+1+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+1+00
Sat, Sep 26, 2026+1+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+0+00
Wed, Sep 30, 2026+1+00
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+00
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+1+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+00
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+4+00
Sat, Oct 17, 2026+1+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+00
Total+104+70
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Sep 91 post

    • 别再让世界模型评测只交出一个无法复核的分数。 HarnessEval-W 按案例路由评估技能，拆出可测子问题，由专门子 Agent 检查视频中的物理、因果和状态变化，再由父 Agent 验证证据、汇总结果。问题、答案、分数和支持帧都会留档，且路由不依赖被测模型。它把 Agent 的 Tool Use 推向了模型审计，不过三套环境和多个后端也意味着部署不算轻。

      Read full on X, posted by @vintcessun

      @vintcessun · x.com

  2. 22 days earlier
  3. Aug 182 posts

    • HarnessEval-W turns a world-model score into an actual execution chain: route the case, split the task across specialist agents, inspect rollout evidence, then validate the result. Evaluation just…

      Read full on X, posted by @osanpochuudayo

      @osanpochuudayo · x.com

    • HarnessEval-W: Agentifying the Evaluation of Visual Worlds A new benchmark that brings the harness paradigm to world model evaluation, using specialized sub-agents to produce transparent, auditable…

      Read full on X, posted by @HuggingPapers

      @HuggingPapers · x.com

You might also like

Repositories close to MirroS-Lab/HarnessEval-W
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

AxiomCode

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Busbar

Control what AI can do before it acts

meituan-longcat/WBench

Python

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

25014

open-compass/AgentCompass

Python

[EMNLP 2026] AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.

16836

galilai-group/stable-worldmodel

Python

A platform for reproducible world model research and evaluation

2.3k293

TriWorldBench/TriWorldBench

Python

A Benchmark Evaluating Triple-View Embodied World Models

2361

camel-ai/crab

Python

🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/

43065

OpenEnvision/WorldFoundry

Python

Unified World Model Inference & Evaluation Infrastructure

32024

tsinghua-fib-lab/World-Model

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

87041

harbor-framework/terminal-bench

Python

Measuring and evolving with the frontier of agent work

929602

claw-eval/claw-eval

Python

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

77877