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
ClawBench
ClawBench
Bifrost
Bifrost

arcprize/arc-agi-3-benchmarking

#LLM evaluation
Visit GitHub
Python
56
24
6 contributors
MIT License
FeaturedAdvertise to 180K+ monthly visitors
ClawBench

a benchmark for personal agents

Bifrost

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

Momentum

How fast arcprize/arc-agi-3-benchmarking 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 25 – Oct 24, 2026

Stars +21 in 61 days

012
2

Forks +10 in 61 days

01
1

Merged PRs 18 in 61 days

012
2

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

Not in the Trendshift top 25 in this period

Aug 25Sep 2Sep 10Sep 18Sep 26Oct 4Oct 12Oct 20
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
Tue, Aug 25, 2026+0+10
Wed, Aug 26, 2026+0+00
Thu, Aug 27, 2026+1+00
Fri, Aug 28, 2026+0+00
Sat, Aug 29, 2026+0+00
Sun, Aug 30, 2026+0+00
Mon, Aug 31, 2026+0+00
Tue, Sep 1, 2026+0+10
Wed, Sep 2, 2026+0+00
Thu, Sep 3, 2026+2+11
Fri, Sep 4, 2026+2+00
Sat, Sep 5, 2026+0+10
Sun, Sep 6, 2026+2+10
Mon, Sep 7, 2026+0+10
Tue, Sep 8, 2026+0+10
Wed, Sep 9, 2026+0+11
Thu, Sep 10, 2026+2+00
Fri, Sep 11, 2026+0+00
Sat, Sep 12, 2026+1+00
Sun, Sep 13, 2026+1+00
Mon, Sep 14, 2026+0+00
Tue, Sep 15, 2026+2+01
Wed, Sep 16, 2026+1+01
Thu, Sep 17, 2026+1+10
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+0+01
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+0+01
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+1+00
Fri, Sep 25, 2026+0+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+0+00
Wed, Sep 30, 2026+0+02
Thu, Oct 1, 2026+1+00
Fri, Oct 2, 2026+0+02
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+2+00
Mon, Oct 5, 2026+1+00
Tue, Oct 6, 2026+0+01
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+1+01
Tue, Oct 13, 2026+0+02
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+02
Fri, Oct 16, 2026+0+01
Sat, Oct 17, 2026+0+00
Sun, Oct 18, 2026+0+10
Mon, Oct 19, 2026+0+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+01
Fri, Oct 23, 2026+0+00
Sat, Oct 24, 2026+0+00
Total+21+1018
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Sep 31 post

    • For ARC-AGI-3 we tested GPT-6 Astra with both our Standard harness (the model decides which notes to carry forward) as well as a new provider adapter harness (which preserves opaque reasoning between…

      Read full on X, posted by @arcprize

      @arcprize · x.com

  2. 1 month earlier
  3. Jul 303 posts

    • ARC-AGI team has not achieved AGI. This is complete bullshit. They have a harness and it has adapters that talk to each of the APIs. I swear they must have vibe coded their code base and not even…

      Read full on X, posted by @jezell

      @jezell · x.com

    • We use the same standard harness for Anthropic/Opus Same completions style endpoint - no reasoning logs passed back The point is to be consistent across providers

      Read full on X, posted by @GregKamradt

      @GregKamradt · x.com

    • Source? We used the same "rolling window" convention for Opus/Anthropic that we did for OpenAI

      Read full on X, posted by @GregKamradt

      @GregKamradt · x.com

  4. Jul 241 post

    • ARC-AGI-1 Claude Opus 5 scores 97.5% for $0.70/task This is competitive with previous SOTA performance for slightly higher cost

      Read full on X, posted by @arcprize

      @arcprize · x.com

  5. Jul 231 post

    • We found that Grok 4.5 (High) performance was in line with GPT 5.6 Luna (Max)

      Read full on X, posted by @arcprize

      @arcprize · x.com

  6. 14 days earlier
  7. Jul 91 post

    • Sol, Terra and Luna all push the pareto frontier towards more efficient performance ARC-AGI-2 * Sol: 92%, $1.44/task * Terra: 83.9%, $1.09/task * Luna: 59.5%, $0.67/task ARC-AGI-1 * Sol: 96.5%,…

      Read full on X, posted by @arcprize

      @arcprize · x.com

  8. 1 month earlier
  9. Jun 11 post

    • Testing notes: * ARC-AGI-3 Prompt Update - We observed that in our original system prompt, GPT and Gemini, unlike other models, would not "think out loud" in their reply. This caused them to *only*…

      Read full on X, posted by @arcprize

      @arcprize · x.com

You might also like

Repositories close to arcprize/arc-agi-3-benchmarking
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

ClawBench

a benchmark for personal agents

theredbluepill/arc-interactive

Python

A collection of community game environments for the ARC-AGI-3 benchmark.

579

NIMI-research/Tycho

Python

ARC-AGI-3 Solver using Rendered Deterministic Moore Machines

6211

strands-labs/benchmark-harnesses

Python

Strands-based agents and harnesses for agentic benchmarks.

659

poetiq-ai/poetiq-arc-agi-solver

Python

This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

1.3k216

arcprize/arc-agi-benchmarking

Python

Testing baseline LLMs performance across various models

36573

harbor-framework/terminal-bench

Python

Measuring and evolving with the frontier of agent work

966610

symbolica-ai/arcgentica

Python

An ARC-AGI solution using Agentica from Symbolica

31025

ZJU-REAL/ageval

Python

Agent eval on one running base. Swap the agent under test with plugins; run the same dataset anywhere.

732

Exgentic/exgentic

Python

General agent evaluation framework

7623