AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 30 October 2026

Does Serper find the less famous namesake when something more famous shares its name?

Serper found the intended subject despite its more famous namesake. All ten results concerned Grafana Labs’ Loki, and snippets at ranks 1, 4 and 10 pointed to the compactor.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

The test case

Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.

Something more famous has the same namePassEvidence
What we sent

“In Loki, the log aggregation system from Grafana Labs, which configuration block does retention_enabled have to be set in for old log data to actually be deleted?”

What the tool returned
JSON
[
  {
    "rank": 1,
    "url": "https://grafana.com/docs/loki/latest/operations/storage/retention/",
    "title": "Log retention | Grafana Loki documentation",
    "content": "Retention in Grafana Loki is achieved through the Compactor. By default the compactor.retention-enabled flag is not set, so the logs sent to Loki live forever.",
    "content_chars": 159,
    "published_date": null
  },
  {
    "rank": 2,
    "url": "https://community.grafana.com/t/loki-log-retention-policy-and-period/153531",
    "title": "Loki log retention policy and period - Grafana community forums",
    "content": "I have configured a log retention policy in Loki to store logs for 30days, but someway somehow my logs are being kept for only 10 days. here ...",
    "content_chars": 144,
    "published_date": "Jun 27, 2025"
  },
  {
    "rank": 3,
    "url": "https://community.grafana.com/t/loki-does-not-delete-logs-after-retention-delete-delay/81898",
    "title": "Loki does not delete logs after retention delete delay",
    "content": "Checking on Grafana after five minutes but the logs are still there. I maybe is the retention_delete_delay that should not be set to 5 minutes?",
    "content_chars": 143,
    "published_date": "Feb 16, 2023"
  },
  {
    "rank": 4,
    "url": "https://grafana.com/docs/loki/latest/operations/storage/logs-deletion/",
    "title": "Log entry deletion | Grafana Loki documentation",
    "content": "Configuration. Enable log entry deletion by setting retention_enabled to true in the compactor's configuration ( -compactor.retention-enabled on the command ...",
    "content_chars": 160,
    "published_date": null
  },
  {
    "rank": 5,
    "url": "https://www.youtube.com/watch?v=h_GGd7HfKQ8",
    "title": "Meet Grafana LOKI, a Log Aggregation System for EVERYTHING",
    "content": "I've been on a quest to find a new logging system. I've use quite a few in the past, some open source, some proprietary, and some home grown ...",
    "content_chars": 144,
    "published_date": "4 years ago"
  },
  {
    "rank": 6,
    "url": "https://community.grafana.com/t/how-grafana-loki-retention-works/67754",
    "title": "How Grafana Loki retention works",
    "content": "I would like to set up retention for logs stored in Grafana Loki and I am not sure how the retention really works. There is more period time ...",
    "content_chars": 144,
    "published_date": "Jun 26, 2022"
  },
  {
    "rank": 7,
    "url": "https://oneuptime.com/blog/post/2026-01-30-loki-retention-strategies/view",
    "title": "How to Implement Loki Retention Strategies",
    "content": "Managing log retention in Grafana Loki requires understanding how Loki stores data and which components handle deletion.",
    "content_chars": 120,
    "published_date": "Jan 30, 2026"
  },
  {
    "rank": 8,
    "url": "https://community.grafana.com/t/loki-retention-policy-and-chunk-deletion-issue/159057",
    "title": "LOKI Retention Policy and Chunk Deletion Issue",
    "content": "How can we make sure chunks are actually deleted after retention (and not just marked)?. Is there a better approach to enforce retention-based ...",
    "content_chars": 146,
    "published_date": "Nov 3, 2025"
  },
  {
    "rank": 9,
    "url": "https://community.grafana.com/t/log-retention-policy/116009",
    "title": "Log retention policy - Grafana Loki",
    "content": "Despite the configuration file specifying a retention period of 'period: 24h', I'm seeing old logs persisting. Can you help clarify the ...",
    "content_chars": 139,
    "published_date": "Mar 4, 2024"
  },
  {
    "rank": 10,
    "url": "https://medium.com/@aditya.hilman_10961/enabling-log-retention-in-loki-with-compactor-fe3de2002b47",
    "title": "Enabling Log Retention in Loki with Compactor",
    "content": "compactor.retention_enabled: true Enables the retention policy enforcement in Loki. Without this, the compactor will not delete old logs.",
    "content_chars": 137,
    "published_date": null
  }
]

Serper search record with ten Loki results

Copied from Output file (JSON), results

Open the whole JSON file ↗
Expected vs. Found
✓Expected: The results are about the intended subject.Found: All ten results concerned Grafana Labs’ Loki log aggregation system, rather than its more famous namesake.
Why this result

The question reached Serper and the search completed. All ten results concerned the intended subject, meeting the requirement to find the right namesake.

Also observed in this test case

Returned pages. The two reference pages, grafana.com/docs/loki/ and grafana.com/oss/loki/ (both Loki landing pages), did not come back; Serper returned the more specific retention pages at ranks 1 and 4, which answer the question more directly.

Snippets only. The search returned ranked results with snippets, not a written answer.

Tested by Aman · evidence dated 23 September 2026

Configuration and setup

How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.

Software that produced the output
Serper
Build or version
Not exposed by the hosted product
Surface
API
Set up before the run
Loki shares its name with Marvel’s Loki. The question names Grafana Labs’ log aggregation system. The answer, the compactor block, was confirmed against Grafana’s Loki documentation on 23 September 2026. Reference pages: grafana.com/docs/loki/ and grafana.com/oss/loki/. Google search, 10 results, no site restriction.
Search
Google · 10 results · no domain restriction
Tested
23 September 2026 · Aman

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.

The rules
  • Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
  • Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
  • Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.

Where this sits in the benchmark

This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.

LevelNameScope
BenchmarkWeb Search for AI →10 scenarios · 12 tools
CapabilityWeb Retrieval →
ScenarioSomething more famous has the same name →
ToolSerper →

History of this result

What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.

from the publication record
10 November 2026First publishedWeb Search for AI v1

Act on this result

Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/web-search-for-ai/results/serper/name-disambiguation · 1 pass · 0 fail · coverage 1/1 · graded 2026-10-30

The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.

Verify the proof files

These files support this result. Open a file to inspect the original evidence.

Output file (JSON) ↗application/json · 11 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Output file (JSON)f2678b44871cdee51cc94bdfe55e69e151d1c2d416e19615bb79307c607deb63