Cross-model benchmark
Cross-Model Legal Benchmark
HAQQ's own measured benchmark scoring legal AI models out of 50 across legal task categories.
AI Model Performance on Legal Tasks
HAQQ's own independent cross-model legal benchmark: 19 models scored out of 50 across 11 real legal tasks - from contract drafting and legal research to NDAs and shareholder agreements. This is HAQQ's measured benchmark (published in full on our comparison pages), not a third-party ranking; specialists lead on their home turf and no model wins every task.
| Model | Average / 50 | Legal | Contract Drafting | Legal Research | Law Explanation | Employment Agreement | Memo Drafting | License Agreement | Shareholder Agreement | Consultancy Agreement | Commercial Agreement | NDA Drafting |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HAQQ (Justinian) | 45.8 | 49 | 44 | 43 | 42 | 48 | 44 | 46 | 47 | 45 | 47 | 49 |
| Claude Fable 5 | 42.7 | 45 | 45 | 41 | 43 | 43 | 41 | 42 | 42 | 42 | 41 | 45 |
| Claude Opus 4.7 | 40.8 | 43 | 43 | 39 | 39 | 39 | 41 | 43 | 40 | 39 | 42 | 41 |
| Mike OS | 39.1 | 42 | 39 | 35 | 33 | 41 | 39 | 38 | 41 | 40 | 40 | 42 |
| Harvey | 37.9 | 38 | 40 | 32 | 27 | 42 | 34 | 39 | 44 | 38 | 43 | 40 |
| DeepSeek v4 Pro | 36.8 | 40 | 36 | 38 | 38 | 35 | 37 | 36 | 36 | 36 | 37 | 36 |
| CoCounsel | 36.6 | 37 | 38 | 40 | 31 | 37 | 42 | 35 | 37 | 34 | 35 | 37 |
| Legora | 35.9 | 33 | 42 | 27 | 26 | 40 | 30 | 40 | 39 | 41 | 38 | 39 |
| ChatGPT 5.5 | 35.3 | 39 | 34 | 34 | 45 | 33 | 35 | 32 | 32 | 35 | 34 | 35 |
| Claude + legal plugins | 33.9 | 35 | 35 | 33 | 35 | 34 | 33 | 34 | 34 | 33 | 33 | 34 |
| Gemini 3.1 Pro | 32.9 | 36 | 32 | 36 | 41 | 30 | 32 | 31 | 30 | 30 | 31 | 33 |
| Spellbook | 32.9 | 27 | 46 | 18 | 20 | 38 | 20 | 41 | 35 | 37 | 36 | 44 |
| LexisNexis +AI | 32 | 36 | 29 | 46 | 28 | 30 | 38 | 28 | 31 | 27 | 29 | 30 |
| Grok 4.3 | 30.7 | 33 | 31 | 26 | 36 | 28 | 29 | 29 | 28 | 31 | 35 | 32 |
| Perplexity Sonar | 27.2 | 29 | 22 | 43 | 34 | 24 | 28 | 23 | 23 | 25 | 24 | 24 |
| Clio Duo | 25.6 | 26 | 27 | 24 | 23 | 28 | 23 | 25 | 24 | 29 | 26 | 27 |
| Meta Llama 4 | 23.8 | 24 | 23 | 23 | 29 | 23 | 24 | 22 | 22 | 24 | 23 | 25 |
| Mistral 3 | 22.4 | 22 | 25 | 20 | 25 | 21 | 22 | 24 | 20 | 22 | 22 | 23 |
| Qwen 3 Plus | 18.7 | 19 | 18 | 21 | 22 | 17 | 18 | 18 | 17 | 19 | 18 | 19 |
Measured data - pre-processed from HAQQ's real Legal AI Index usage dataset (134,000+ data points across 30 countries) or HAQQ's own /50 cross-model legal benchmark.
Related research
Multi-Model Strategy in Legal
How many AI models firms run, and the criteria they weigh when choosing.
Risk & Hallucination Rates
Estimated error rates across legal tasks, highest for citation and jurisdiction work.
Competitive Landscape Map
Legal AI vendor categories, vendor counts and growth rates across the market.
Part of the HAQQ Legal AI Index
Cross-Model Benchmark
HAQQ's measured benchmark scoring legal AI models out of 50.
Legal AI Index
The full data report on how AI is used across the legal ecosystem.
Legal Agent Study
All-pass rubric grading of AI agents on long-horizon legal work.
Research Hub
Browse every legal AI research graph in one place.