GoodTime vs candidate.fyi
Two of twelve models named GoodTime first on the direct prompt; zero named candidate.fyi. GoodTime was named by twelve of the twelve models and candidate.fyi by six and GoodTime carries 45 labels and candidate.fyi 11, so the shares are not directly comparable.
Named in two categories this edition.
Named in one category this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all twelve models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the interview scheduling page.
By framing
GoodTimeFirst choices, of twelve modelscandidate.fyi
Across every category in the September 2026 Edition, GoodTime and candidate.fyi were named in the same answer fifty-three times, of the 135 answers naming GoodTime and the 59 naming candidate.fyi. In those answers candidate.fyi took the first choice ten times and GoodTime twenty-one.
Every model, every framing
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | | |||||
| GPT-5.4 mini | | | | | ||
| Gemini 3.5 Flash | | | | | | |
| Perplexity Sonar | | | | | ||
| Grok 4.1 Fast | | | | | | |
| Mistral Small | | | | |||
| DeepSeek V4 Flash | | | | | | |
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | | | | | | |
| Kimi K2 | | | | |||
| GLM 4.7 FlashX | | | ||||
| MiniMax M2.5 | | | |
GoodTime candidate.fyi first choice named as an alternative argued againstblank: not namedEach cell is one answer, GoodTime on the left and candidate.fyi on the right.The direct prompt
GoodTime first, candidate.fyi not the choice
2 of 12 modelscandidate.fyi was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
6 of 12 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
4 of 12 modelsThe answer made no first choice from these two in this category.Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
By buyer segment
GoodTime0%#10 of 11candidate.fyi0%#– of 11GoodTime9%#5 of 11candidate.fyi6%#7 of 11GoodTime56%#1 of 9candidate.fyi21%#2 of 9What the models said about GoodTime
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Avoid ATS-style recruiting platforms like Breezy HR, Workable, or GoodTime if budget is tight” Perplexity Sonar · budget prompt · hard negative
“Enterprise, quote-only, often thousands per month — avoid these on a limited budget” DeepSeek V4 Flash · budget prompt · hard negative
“Frequent reports of bugs like missing time slots, crashes, slow performance, calendar sync glitches, and timezone issues.” Grok 4.1 Fast · negative prompt · soft negative
“Choose GoodTime if you have a dedicated recruiting team and want to automate the administrative side of interviewing” Qwen 3.7 Flash · comparative prompt · first choice
“GoodTime is the top choice for enterprises whose scheduling challenge extends beyond simple booking” Claude Haiku 4.5 · comparative prompt · first choice
“Best overall for mid-market recruiting teams: GoodTime if you run multi-interviewer panels” GPT-5.4 mini · direct prompt · first choice
What the models said about candidate.fyi
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“Built specifically for companies of your size. Strong zero-click automation, heavy interviewer training logic, and branded portals.” Gemini 3.5 Flash · scale prompt · first choice
“prioritize tools with panel support like GoodTime alternatives (e.g., candidate.fyi, ModernLoop)” Grok 4.1 Fast · negative prompt · first choice
“Best for complex panels/enterprise orchestration: GoodTime, candidate.fyi” Kimi K2 · scale prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.