Is claude-opus-4.6-medium good at Knowledge & Docs?
claude-opus-4.6-medium ranks #54 of 94 for Knowledge & Docs — usable. The top pick for this task is gpt-5.4-max.
claude-opus-4.6-medium on each Knowledge & Docs sub-task
| Grounded Docs (No Fabrication) | 99.0/100 | #59 |
| Help-Center Article | 97.5/100 | #66 |
| Right Doc Type | 72.0/100 | #50 |
| Procedure / Runbook | 41.5/100 | #82 |
Real examples, graded
WeakRunbook: rotate a production credential (Northwind) 26/100
“The response contains severe fabrications of menu paths and API endpoints, and crams multiple actions into single steps.”
WeakHelp article: filter the review queue (Ferrovia) 42/100
“The model successfully structures the article and answers the main task using the provided facts. However, in the troubleshooting section, it invents a 'connection status' and error states on the Integrations page, which are not in the provided facts. Per the gating rules, any fabricated UI or behavior sets grounding to 2/10 and caps the overall score.”
Frequently asked
Is claude-opus-4.6-medium good at Knowledge & Docs?
claude-opus-4.6-medium ranks #54 of 94 models we tested for Knowledge & Docs, scoring usable.
What is claude-opus-4.6-medium's strongest Knowledge & Docs skill?
Its best sub-task here is Grounded Docs (No Fabrication).
This page is Spring Prompt, running
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals