Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Information retrieval at 80.0, weakest is Delegated access at 25.0.
Site checks by category
Brand awareness
40.0
Discovery
35.0
Information retrieval
80.0
Market ranking
25.0
Accuracy
65.0
Task completion
45.0
Delegated access
25.0
Contact & communication
50.0
01 Site checks
Points by category
Brand awareness
40.0
Discovery
35.0
Information retrieval
80.0
Market ranking
25.0
Accuracy
65.0
Task completion
45.0
Delegated access
25.0
Contact & communication
50.0
02 Agent sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
1m 14s
93median 93
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
1m 52s
90median 93
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
5m 39s
93median 93
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
10m 34s
90median 93
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
5m 10s
62median 93
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
15m 44s
80median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
46s
73median 69
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
1m 12s
62median 69
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
3m 7s
36median 69
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
6m 47s
36median 69
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
3m 20s
36median 69
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
6m 31s
62median 69
Information retrieval
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 14s
85median 74
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 53s
93median 74
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
5m 38s
85median 74
Market ranking
Based on your knowledge, name 3 direct competitors to aiinterconnect.com in the same developer-tools category and rank them by developer…
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
12s
54median 54
Based on your knowledge, name 3 direct competitors to aiinterconnect.com in the same developer-tools category and rank them by developer…
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
18s
58median 54
Based on your knowledge, name 3 direct competitors to aiinterconnect.com in the same developer-tools category and rank them by developer…
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
9s
32median 54
Accuracy
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
1m 14s
94median 70
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
1m 52s
94median 70
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
5m 37s
94median 70
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
46s
90median 79
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
1m 12s
93median 79
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
3m 7s
94median 79
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
6m 47s
66median 79
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
3m 19s
39median 79
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
6m 30s
80median 79
03 Blend
Agents 60%
Checks 40%
One kind of evidence only? That kind counts in full.
Brand awareness10% of the overall
0.4 × 40.0 + 0.6 × 83.3 = 66.0 raw
66.0 raw → 82.9 published
Discovery15% of the overall
0.4 × 35.0 + 0.6 × 31.7 = 33.0 raw
33.0 raw → 60.7 published
Information retrieval15% of the overall
0.4 × 80.0 + 0.6 × 75.0 = 77.0 raw
77.0 raw → 88.9 published
Market ranking10% of the overall
0.4 × 25.0 + 0.6 × 21.0 = 22.6 raw
22.6 raw → 51.2 published
Accuracy15% of the overall
0.4 × 65.0 + 0.6 × 88.0 = 78.8 raw
78.8 raw → 89.8 published
Task completion20% of the overall
0.4 × 45.0 + 0.6 × 84.3 = 68.6 raw
68.6 raw → 84.4 published
Delegated access10% of the overall
Site checks only: 25.0 raw
25.0 raw → 53.6 published
Contact & communication5% of the overall
Site checks only: 50.0 raw
50.0 raw → 73.2 published
Category
Weight
Checks
Sessions
Blend
Benchmarked
Brand awareness
10%
40.0
83.3
66.0
82.9
Discovery
15%
35.0
31.7
33.0
60.7
Information retrieval
15%
80.0
75.0
77.0
88.9
Market ranking
10%
25.0
21.0
22.6
51.2
Accuracy
15%
65.0
88.0
78.8
89.8
Task completion
20%
45.0
84.3
68.6
84.4
Delegated access
10%
25.0
None
25.0
53.6
Contact & communication
5%
50.0
None
50.0
73.2
Overall
100%
~55.9
77.0
04 Benchmarked score
55.9 raw → 77.0
Final score is calibrated and adjusted to better reflect the actual performance and benchmark.
Category weights
Brand awareness 10%
Discovery 15%
Information retrieval 15%
Market ranking 10%
Accuracy 15%
Task completion 20%
Delegated access 10%
Contact & communication 5%
Overall 77.0, from 55.9 raw points.
Agents
Each agent’s score over 30 days, and how its latest sessions went.
Claude
Latest run average
83.1
Developer tools median
88.4
Sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
1m 14s
93median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
46s
73median 69
Information retrieval
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 14s
85median 74
Market ranking
Based on your knowledge, name 3 direct competitors to aiinterconnect.com in the same developer-tools category and rank them by developer…
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
12s
54median 54
Accuracy
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
1m 14s
94median 70
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
46s
90median 79
ChatGPT Agent
Latest run average
83.6
Developer tools median
84.1
Sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
1m 52s
90median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
1m 12s
62median 69
Information retrieval
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 53s
93median 74
Market ranking
Based on your knowledge, name 3 direct competitors to aiinterconnect.com in the same developer-tools category and rank them by developer…
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
18s
58median 54
Accuracy
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
1m 52s
94median 70
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
1m 12s
93median 79
Gemini
Latest run average
78.4
Developer tools median
83.0
Sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
5m 39s
93median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
3m 7s
36median 69
Information retrieval
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
5m 38s
85median 74
Market ranking
Based on your knowledge, name 3 direct competitors to aiinterconnect.com in the same developer-tools category and rank them by developer…
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
9s
32median 54
Accuracy
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
5m 37s
94median 70
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
3m 7s
94median 79
Kimi
Latest run average
68.6
Developer tools median
Too few sites yet for a median
Sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
10m 34s
90median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
6m 47s
36median 69
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
6m 47s
66median 79
Llama
Latest run average
47.4
Developer tools median
Too few sites yet for a median
Sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
5m 10s
62median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
3m 20s
36median 69
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
3m 19s
39median 79
Grok
Latest run average
74.3
Developer tools median
Too few sites yet for a median
Sessions
Brand awareness
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
15m 44s
80median 93
Discovery
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
6m 31s
62median 69
Task completion
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
6m 30s
80median 79
Excellent85+
Good72-84
OK58-71
Poor40-57
Critical<40
Latest run 6 Oct 2026 (UTC). Sign in to request a re-run from 7 Oct 2026, 18:41 UTC.
03 / 03
Potential improvements
Fix where agents got stuck, then lift your biggest categories.
HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
Biggest wins
Projected
Lifting Discovery to Good adds about +1.4 on its own, taking the overall from 77.0 to 78.4.
Raise Discovery from 60.7 to 72 (Good) to add about 1.4 to the overall score.