Entidex · Signal Layer
We probe Claude, ChatGPT, Gemini, Grok and Perplexity at regular intervals and grade their answers against a known ground truth. The result is a live picture of LLM awareness lag — per model, per topic, with retrieval on or off.
Tracking awareness scores for American Academy of Arts and Sciences over recent probes.
How well each LLM knows American Academy of Arts and Sciences — by topic and retrieval mode.
| Model | Retrieval OFF | Retrieval ON |
|---|---|---|
| ●Claude | 85 | 79 |
| ●ChatGPT | 82 | 82 |
| ●Gemini | 85 | 82 |
| ●Grok | 82 | 82 |
| ●Perplexity | 85 | 85 |
| Model | Retrieval OFF | Retrieval ON |
|---|---|---|
| ●Claude | 69 | 79 |
| ●ChatGPT | 72 | 85 |
| ●Gemini | 75 |
| Model | Retrieval OFF | Retrieval ON |
|---|---|---|
| ●Claude | 82 | 79 |
| ●ChatGPT | 82 | 82 |
| ●Gemini | 82 | 85 |
| ●Grok | 62 | 72 |
| ●Perplexity | 85 | 85 |
| ●Grok | 39 | 85 |
| ●Perplexity | 85 | 85 |
