To evaluate an AI model on ARC-AGI, name the benchmark edition and evaluation split, follow that edition’s scoring rules, record the model and reasoning configuration, and report accuracy alongside cost and runtime. An ARC-AGI score is meaningful only with those conditions attached: ARC-AGI-1 and ARC-AGI-2 use static grid tasks, while ARC-AGI-3 is interactive and its results are not directly comparable.
What does an ARC-AGI evaluation measure?
In ARC-AGI-1 and ARC-AGI-2, a solver sees a small set of input-output grid examples, infers the transformation rule, and applies it to a new input. ARC-AGI-2 is designed to test more involved reasoning, including interpreting symbols by their meaning, combining interacting rules, and applying rules differently depending on context. ARC-AGI-3 instead evaluates performance in interactive environments, so it measures a different task format.
ARC Prize describes its goal as examining not only whether a system can solve a task, but also the efficiency or cost of doing so. A score without resource information can obscure how much computation or repeated search produced it.
Which edition and evaluation split should you use?
Choose the edition first, then identify the exact split. ARC Prize’s ARC-AGI-2 materials distinguish public tasks from withheld evaluation sets; a public-set result is not evidence of the same performance on private tasks.
The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
| ARC-AGI-2 split | What it contains | How to describe a result |
|---|---|---|
| Public training | 1,000 public training tasks, according to the ARC-AGI-2 repository README (accessed 2026). | Use for development and clearly label any score as a training-set result. |
| Public evaluation | 120 public evaluation tasks, according to the repository README (accessed 2026). | Name it explicitly as the public evaluation split; do not present it as a private-set result. |
| Semi-private evaluation | An additional 120-task set intended for remotely hosted commercial models. | State that the result is semi-private and identify the evaluation arrangement when known. |
| Private evaluation | A separate 120-task set used in the competition. | Call it private only when the evaluation actually used that set. |
The repository README reports 66% average human performance on its public evaluation tasks in a test sample. That figure describes the sample, not a guaranteed score for every person. ARC Prize’s benchmark page says the public, semi-private, and private evaluation tasks were calibrated so that each was solved by at least two humans within two attempts. Its account of the calibration process describes a live study with more than 400 members of the general public in San Diego in early 2025; this is a task-solvability criterion, not a claim that every participant achieved a perfect score.
How is ARC-AGI-2 scored?
For the 2026 ARC Prize competition, each test input permits exactly two predicted outputs. A test output earns 1 if either prediction exactly matches the expected grid, and 0 otherwise; the final score is the average across task test outputs. This is commonly described as an exact-match pass@2 score. Report the scoring rule and attempt allowance with the percentage, rather than treating the score as a generic measure of accuracy. Other editions or evaluation protocols may differ, so verify the applicable rules before comparing results.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
How to run and document a useful evaluation
- Select the edition. State ARC-AGI-1, ARC-AGI-2, or ARC-AGI-3. Do not merge static-grid and interactive results.
- Name the split and exposure. Record whether the tasks were public, semi-private, or private, and whether the evaluation used a hosted or local setup where relevant.
- Freeze the system configuration. Record the model name, reasoning level, token limits, prompts, code, task interface, permitted tools, and number of attempts. ARC Prize’s Verified Testing Policy specifically calls for model name, reasoning level, and token limits for a new model configuration.
- Apply the edition’s scoring protocol. For the 2026 ARC-AGI-2 competition metric, allow exactly two outputs per test input and count an exact match in either position as a pass for that test output.
- Measure resources as well as accuracy. Report cost per task and total evaluation duration when available, and explain the accounting boundary—for example, which inference or search costs are included—if that information is known.
- Label verification status. Distinguish a result listed as verified by ARC Prize from a self-run experiment or community leaderboard entry. ARC Prize says it does not verify submissions by default and adds verified models selectively.
- Retain the run details. Keep the individual task scores, outputs, configuration, costs, duration, and evaluation conditions so another reader can interpret or reproduce the aggregate. ARC Prize’s policy identifies public outputs, durations, costs, and individual task scores among published result fields.
How should you compare two ARC-AGI results?
Compare results only after matching the conditions that determine what the number means. A higher percentage is not automatically a better or more efficient system if it used a different split, more attempts, a different scoring rule, or substantially greater resources.
- Edition and split: require the same ARC-AGI version and evaluation split.
- Scoring and attempts: match the exact scoring rule and output or attempt budget.
- Configuration: compare model version, reasoning level, token limits, and relevant tools.
- Efficiency: review cost per task and total duration using comparable cost accounting.
- Verification and harness: distinguish verified from self-reported results; for ARC-AGI-3, identify the harness used.
- Date: attach a date because results, configurations, and competition rules can change.
What do published ARC-AGI scores show?
Published figures illustrate why edition, split, date, and configuration belong beside every score. The figures below describe different evaluations and should not be read as a direct head-to-head comparison.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
| Result | Reported performance | Conditions and qualification |
|---|---|---|
| ARC Prize 2025 global competition | 24% top score on ARC-AGI-2 private evaluation; $0.20 per task | ARC Prize Foundation’s 2026 technical report identifies this as the top score in the competition, which ran March 26–November 3, 2025. The competition had 1,455 teams and 15,154 entries. |
| OpenAI GPT-6 Astra verified results | ARC-AGI-2 scores ranged from 59.6% with no reasoning to 95.0% with max reasoning | ARC Prize’s results page labels this model-specific verified entry September 2, 2026. The range spans listed reasoning variants; it is not a result for every model or evaluation environment. |
The same GPT-6 Astra results page reports different ARC-AGI-3 figures for Standard and Provider Adapter harnesses. That is a practical example of why interactive benchmark scores need the harness named rather than being collapsed into one number.
What limitations should accompany an ARC-AGI score?
- Exposure and contamination: public tasks support development, but exposure makes them different evidence from withheld evaluation tasks. State the split and do not imply that public performance establishes private-set performance.
- Selective verification: verification is not automatic for every submission. Use “verified” only for results ARC Prize lists as verified.
- Edition changes: ARC-AGI-2 asks different reasoning questions from ARC-AGI-1, and ARC-AGI-3 changes to interactive environments. Score changes across editions are not a clean trend on one fixed test.
- Efficiency accounting: cost and duration matter, but comparisons are meaningful only when the accounting boundaries and system setup are sufficiently comparable.
- Changing results: date leaderboards and model configurations, and check the applicable competition rules when reporting a result.
Where to find the official evaluation materials
Use ARC Prize’s ARC-AGI-1 & ARC-AGI-2 Guide for the official entry point on data structure, tools, and solution approaches, alongside the relevant edition’s repository, benchmark description, testing policy, competition rules, and results page. The names of these official resources are provided here because no source URLs accompany this assignment; no links are inferred.
Quick Recap
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
