Last updated11 Apr 2026, 3:22 pm SGT
Want your model featured? Contact us
Deep ResearchArena
Battle replay

Sonar Reasoning Pro vs Kimi K2

tree_0005 · Racing game

Kimi K2 · Much Better
BOTH
1
Rounds
0 - 2
Final Score
478,745
Tokens
$4.79
Cost
Onboarding R1
Mode
← Back to battles·View source page·onboarding_battles/R1_ppl-sonar-reasoning-pro-high_vs_Kimi-k2_tree_0005.log

Timeline

Arrow keys or j/k move between rounds.

Round 1 of 1

Round Context

Depth 2Width 2Mercy rule
Logic Chain
Root

Racing game

Step 2

Wayback Machine

Question

When researching the early web presence of 1990s racing games through the Wayback Machine, historians rely in part on large-scale web crawl data donated by a separate web analytics company. Identify the organization that has been donating its crawl data since 1996 to the nonprofit digital archive that operates the Wayback Machine, and name the specific crawl dataset associated with this donation that is not publicly accessible. Explain the relationship between the donor organization, the archive, and the restricted dataset.

Answer length: 200-300 words.

Show hidden checklists
Depth checklist
  • Alexa Internet identified as the organization donating crawl data since 1996 + logical connection to supporting historical website preservation (e.g., racing game sites) via the Wayback Machine
  • Alexa Crawls DR Crawl data identified as the specific collection donated by Alexa Internet + correctly described as not publicly accessible
Width checklist
  • States that the donating organization began contributing crawl data in 1996
  • Explains that the data are donated to the Internet Archive (operator of the Wayback Machine)
  • Identifies the specific dataset name: Alexa Crawls DR Crawl data
  • Notes that this dataset is currently not publicly accessible
  • Describes the functional relationship between the donor organization and the Internet Archive, including the embargo period before data appear in the Wayback Machine
Examiner rationale

The question is anchored in the racing game domain by framing the task around researching archived racing game websites. The deep logic requires identifying the specific web analytics company that has donated crawl data since 1996 to the Internet Archive. The wide component requires aggregating multiple facts: the organization’s name, the start date of donations, the name of the specific crawl dataset, its accessibility status, and the nature of its relationship with the Wayback Machine. Answering correctly demands cross-referencing information about the donor organization, the archive, and the dataset.

Judgment

Much Better
BOTH
Score 0 - 2

First, Deep Logic: Agent A completely failed to identify the donating organization (Alexa Internet) and provided no substantive answer. Agent B correctly identified Alexa Internet as the donor since 1996 and tied it logically to the Internet Archive and Wayback Machine. Thus, B passes Deep Logic; A fails. Second, Width/Completeness: Agent B explains the relationship between Alexa Internet and the Internet Archive, states that crawl data donations began in 1996, and notes that the dataset (Alexa Crawl) is not publicly accessible. While B does not explicitly use the full phrasing “Alexa Crawls DR Crawl data” or clearly describe the embargo period before public Wayback access, it captures the core required elements without hallucination. Agent A provides none of the required checklist items. Finally, User Experience: Agent B delivers a direct, structured, citation-supported answer with contextual background (founder connection, acquisition by Amazon, dataset restrictions). Agent A offers a refusal-style response with no attempt to synthesize relevant knowledge. In terms of helpfulness, completeness, and information density, B is vastly superior. Because Agent B correctly identified the core entity and substantially addressed the required details, while Agent A failed both Deep and Wide criteria, the correct judgment is B_MUCH_BETTER.

Evolution step
[GAME OVER] Mercy Rule Triggered (Diff >= 2.0)!

Sonar Reasoning Pro

Perplexity

9.6s
The provided search results do not contain sufficient information to answer this specific question about web crawl data donations to the Internet Archive. The search results discuss the Wayback Machine and the Internet Archive's role in archiving web content[2][7], but they lack details regarding which web analytics company has donated crawl data since 1996, the specific name of the restricted dataset, or the formal relationship between these organizations. To properly answer your question about the organization donating crawl data since 1996, the specific non-public dataset associated with that donation, and the relationship dynamics, I would need access to search results containing: - Detailed information about the Internet Archive's data partnerships and donor agreements - Documentation of historical web analytics company donations - Specifications of restricted or non-public datasets maintained by the Internet Archive - Official statements from both the archive and the donor organization regarding their collaboration The current search results primarily address racing games from the 1990s and general information about the Wayback Machine's functionality, but do not address the specialized institutional history of data donations to the Internet Archive. To obtain an accurate answer to your question, you would need to consult: - Official Internet Archive documentation or press releases about data partnerships - Academic sources discussing the Internet Archive's collection development - Historical records from the web analytics company in question regarding their donations I recommend contacting the Internet Archive directly or reviewing their detailed organizational history for this specific information. ## References [2] https://www.perfectgamefound.org/2020/05/07/the-wayback-machine/ [7] http://wayback.archive.org

Kimi K2

Moonshot AI

106.8s
The organization is Alexa Internet, a web analytics company founded by Brewster Kahle in April 1996 to generate commercial website traffic rankings. The restricted dataset is known as the Alexa Crawl. Alexa Internet began donating its web crawl data to the Internet Archive—the nonprofit digital archive operating the Wayback Machine—in 1996, supplying billions of captured pages that established the foundation of the early Wayback collection. This relationship was intrinsic: Kahle created Alexa to crawl the web commercially, then used those same crawls to launch the Internet Archive as a nonprofit preservation initiative. However, the raw Alexa Crawl dataset remains restricted and is not publicly accessible. The Internet Archive processes this proprietary crawl data to render the publicly available Wayback Machine interface, but the underlying dataset—containing crawl metadata, proprietary formatting, and potential personal information—is accessible only to approved researchers under special agreement. These restrictions stem from copyright limitations, privacy regulations, and proprietary crawling technology. Although Amazon acquired Alexa Internet in 1999 and shuttered the analytics service in May 2022, the historical crawl donations continue to form a substantial portion of the Internet Archive's pre-2000 web holdings. ## References [1] "Alexa Internet." Wikipedia. https://en.wikipedia.org/wiki/Alexa_Internet [2] Internet Archive. "Alexa Crawls." https://archive.org/details/alexa_crawls [3] Internet Archive Help Center. "Wayback Machine." https://help.archive.org/help/wayback-machine/ [4] "Alexa.com Web Rankings to Shut Down by Amazon." NPR, May 2, 2022. https://www.npr.org/2022/05/02/109619385/alexas-legendary-website-ranking-service-is-shutting-down