Criteria Corp vs Harver
Five of fourteen models named Criteria Corp first on the direct prompt; one named Harver. Criteria Corp was named by thirteen of the fourteen models and Harver by six and Criteria Corp carries 36 labels and Harver 11, so the shares are not directly comparable.
Named in three categories this edition.
Named in three categories this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen 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 candidate assessment page.
By framing
Criteria CorpFirst choices, of fourteen modelsHarver
Across every category in the November 2026 Edition, Criteria Corp and Harver were named in the same answer thirty times, of the 111 answers naming Criteria Corp and the 54 naming Harver. In those answers Harver took the first choice zero times and Criteria Corp six.
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 4.20 | | | | |||
| Mistral Small | ||||||
| DeepSeek V4 Flash | | | | | | |
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | | | ||||
| Kimi K2 | | | | |||
| GLM 4.7 FlashX | | | ||||
| MiniMax M2.5 | | | ||||
| GPT-6 Luna | | | ||||
| Muse Glimmer 30B | |
Criteria Corp Harver first choice named as an alternative argued againstblank: not namedEach cell is one answer, Criteria Corp on the left and Harver on the right.The direct prompt
Both were the first choice
1 of 14 modelsThe answer named them together, and the judge labeled each a first choice.Criteria Corp first, Harver an alternative
4 of 14 modelsHarver was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
5 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
4 of 14 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
Criteria Corp2%#6 of 11Harver0%#– of 11Criteria Corp12%#2 of 12Harver2%#7 of 12Criteria Corp22%#2 of 12Harver0%#11 of 12What the models said about Criteria Corp
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of six in this category shown.
“under investigation by California authorities for potential illegal bias in employment screening” Qwen 3.7 Flash · negative prompt · hard negative
“older or less transparent ones like some legacy SHL, Wonderlic, or Criteria tools” Grok 4.20 · negative prompt · soft negative
“Criteria Corp, Harver, and Plum bundle personality, cognitive, and behavioral assessments in one platform with strong ATS integration” Claude Haiku 4.5 · direct prompt · first choice
“Criteria (by Criteria Corp) stands out as the best overall pre-employment assessment platform for a mid-market B2B company” Grok 4.20 · direct prompt · first choice
“My default pick: Criteria Corp for a mid-market B2B company hiring across several job families.” GPT-6 Luna · direct prompt · first choice
What the models said about Harver
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of four in this category shown.
“heavy reliance on unvalidated or "black-box" AI/personality assessments (e.g., certain features in Harver, Paradox, or generic AI tools)” Grok 4.20 · negative prompt · soft negative
“Criteria Corp, Harver, and Plum bundle personality, cognitive, and behavioral assessments in one platform” Claude Haiku 4.5 · direct prompt · first choice
“include Criteria Corp, TestGorilla, Harver, and HireVue” DeepSeek V4 Flash · scale prompt · alternative
“Solid for high-volume or frontline hiring with good customer support” Grok 4.20 · direct prompt · alternative
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.