Comparison
Harvey vs Spellbook
Where Harvey and Spellbook rank on 7 published boards, and the latest sourced figure for each of 14 metrics.
Harvey
company · harvey.ai
- Boards
- 7
- Figures
- 14
- Sources
- 1
- Mean confidence
- 100%
Spellbook
company · spellbook.legal
- Boards
- 7
- Figures
- 14
- Sources
- 1
- Mean confidence
- 100%
Ranks
Where each ranks
7 published boards across the pair. The higher rank on a shared board is amber.
| Board | Harvey | Spellbook | Ranks higher | As of |
|---|---|---|---|---|
| Legal AI rank | #1score 54.17 | #4score 25 | Harvey | Oct 8, 2026 |
| Legal AI in Anthropic model API answers | #1score 25 | #2score 12.5 | Harvey | Oct 8, 2026 |
| Legal AI citation share | #1score 36.84 | #7score 0 | Harvey | Oct 8, 2026 |
| Legal AI engine breadth | #1score 3 | #2score 3 | Harvey | Oct 8, 2026 |
| Legal AI in Gemini model API answers | #1score 62.5 | #4score 25 | Harvey | Oct 8, 2026 |
| Legal AI in OpenAI model API answers | #1score 75 | #4score 37.5 | Harvey | Oct 8, 2026 |
| Legal AI presence | #1score 43.75 | #5score 14.58 | Harvey | Oct 8, 2026 |
Figures
The latest figure for each
14 sourced metrics, each with its confidence and source.
| Metric | Harvey | Spellbook | As of |
|---|---|---|---|
| Public prompt benchmarkAnthropic citation share | 10.5%100% confidence · Rank.ai Legal AI Prompt Benchmark | 0%100% confidence · Rank.ai Legal AI Prompt Benchmark | Jul 27, 2026 |
| Public prompt benchmarkAnthropic mention coverage | 12.5%100% confidence · Rank.ai Legal AI Prompt Benchmark | 6.3%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkAnthropic recommendation-prompt presence | 25%100% confidence · Rank.ai Legal AI Prompt Benchmark | 12.5%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkCitation share | 36.8%100% confidence · Rank.ai Legal AI Prompt Benchmark | 0%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkEngine breadth | 3 engines100% confidence · Rank.ai Legal AI Prompt Benchmark | 3 engines100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkGemini citation share | 35%100% confidence · Rank.ai Legal AI Prompt Benchmark | 0%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkGemini mention coverage | 50%100% confidence · Rank.ai Legal AI Prompt Benchmark | 12.5%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkGemini recommendation-prompt presence | 62.5%100% confidence · Rank.ai Legal AI Prompt Benchmark | 25%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkMention coverage | 43.8%100% confidence · Rank.ai Legal AI Prompt Benchmark | 14.6%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkOpenAI citation share | 38.9%100% confidence · Rank.ai Legal AI Prompt Benchmark | 0%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkOpenAI mention coverage | 68.8%100% confidence · Rank.ai Legal AI Prompt Benchmark | 25%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkOpenAI recommendation-prompt presence | 75%100% confidence · Rank.ai Legal AI Prompt Benchmark | 37.5%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkRecommendation-prompt presence | 54.2%100% confidence · Rank.ai Legal AI Prompt Benchmark | 25%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
| Public prompt benchmarkReviewed-brand presence share | 30%100% confidence · Rank.ai Legal AI Prompt Benchmark | 10%100% confidence · Rank.ai Legal AI Prompt Benchmark | Oct 8, 2026 |
See how often AI names you.
Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.
- Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
- Who gets namedEvery competitor in the answers, most named first.
- The pages AI readsThe sources behind each answer.
- Three fixesWhat to fix first, with a brief for the first article.