HireWatch
Models select questions for job interviews under different workplace pressures. The benchmark measures how often they select questions classified as unlawful under US employment law.
- Made by
- Huy Nghiem and colleagues
- Released
- November 2026
- Kind
- Law
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Lawlessness
- Subject
- Law
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 4.7 leads with 0.05% among models released by April 2026 Claude Opus 4.7 leads with 0.05% among models released by April 2026
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Claude Opus 4.7 No compliance instruction, temperature 0 0.05%
- 2 Claude 3.5 Haiku No compliance instruction, temperature 0 0.41%
- 3 GPT-5.4 No compliance instruction, temperature 0 0.58%
- 4
Mistral Large 2 Nov 2024, No compliance instruction, temperature 0 1.20%
- 5 Claude Haiku 4.5 No compliance instruction, temperature 0 1.22%
- 6 GPT-5.4 Mini No compliance instruction, temperature 0 1.42%
- 7
Mistral Small 3.1 No compliance instruction, temperature 0 1.96%
- 8 Claude Sonnet 4.6 No compliance instruction, temperature 0 2.47%
- 9
Llama 4 Maverick No compliance instruction, temperature 0 2.89%
- 10
Gemini 2.5 Flash Sep 2025, No compliance instruction, temperature 0 2.91%
- 11
DeepSeek-V3 Mar 2025, No compliance instruction, temperature 0 4.69%
- 12
Gemini 3 Flash No compliance instruction, temperature 0 5.83%
- 13
Qwen3-235B-A22B No compliance instruction, temperature 0 8.58%
- 14
Qwen3.5-9B No compliance instruction, temperature 0 10.1%
- 15 GPT-4.1 mini No compliance instruction, temperature 0 11.8%
- 16
Llama 3.3 70B Instruct No compliance instruction, temperature 0 12.6%
- 17 GPT-4o-mini (snapshot unspecified) No compliance instruction, temperature 0 16.3%
- 18 Gemini 2.5 Pro (snapshot unspecified) No compliance instruction, temperature 0 21.1%
Source: The HireWatch paper
- 1 Claude Opus 4.7 No compliance instruction, temperature 0 0.05%
- 2 Claude 3.5 Haiku No compliance instruction, temperature 0 0.41%
- 3 GPT-5.4 No compliance instruction, temperature 0 0.58%
- 4
Mistral Large 2 Nov 2024, No compliance instruction, temperature 0 1.20%
- 5 Claude Haiku 4.5 No compliance instruction, temperature 0 1.22%
- 6 GPT-5.4 Mini No compliance instruction, temperature 0 1.42%
- 7
Mistral Small 3.1 No compliance instruction, temperature 0 1.96%
- 8 Claude Sonnet 4.6 No compliance instruction, temperature 0 2.47%
- 9
Llama 4 Maverick No compliance instruction, temperature 0 2.89%
- 10
Gemini 2.5 Flash Sep 2025, No compliance instruction, temperature 0 2.91%
- 11
DeepSeek-V3 Mar 2025, No compliance instruction, temperature 0 4.69%
- 12
Gemini 3 Flash No compliance instruction, temperature 0 5.83%
- 13
Qwen3-235B-A22B No compliance instruction, temperature 0 8.58%
- 14
Qwen3.5-9B No compliance instruction, temperature 0 10.1%
- 15 GPT-4.1 mini No compliance instruction, temperature 0 11.8%
- 16
Llama 3.3 70B Instruct No compliance instruction, temperature 0 12.6%
Source: The HireWatch paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.7 | 0.05% | No compliance instruction, temperature 0 | Apr 2026 | Official leaderboard |
| 2 | Claude 3.5 Haiku | 0.41% | No compliance instruction, temperature 0 | Oct 2024 | Official leaderboard |
| 3 | GPT-5.4 | 0.58% | No compliance instruction, temperature 0 | Mar 2026 | Official leaderboard |
| 4 | | 1.20% | No compliance instruction, temperature 0 | Nov 2024 | Official leaderboard |
| 5 | Claude Haiku 4.5 | 1.22% | No compliance instruction, temperature 0 | Oct 2025 | Official leaderboard |
| 6 | GPT-5.4 Mini | 1.42% | No compliance instruction, temperature 0 | Mar 2026 | Official leaderboard |
| 7 | | 1.96% | No compliance instruction, temperature 0 | Mar 2025 | Official leaderboard |
| 8 | Claude Sonnet 4.6 | 2.47% | No compliance instruction, temperature 0 | Feb 2026 | Official leaderboard |
| 9 | | 2.89% | No compliance instruction, temperature 0 | Apr 2025 | Official leaderboard |
| 10 | | 2.91% | No compliance instruction, temperature 0 | Sep 2025 | Official leaderboard |
| 11 | | 4.69% | No compliance instruction, temperature 0 | Mar 2025 | Official leaderboard |
| 12 | | 5.83% | No compliance instruction, temperature 0 | Dec 2025 | Official leaderboard |
| 13 | | 8.58% | No compliance instruction, temperature 0 | Apr 2025 | Official leaderboard |
| 14 | | 10.1% | No compliance instruction, temperature 0 | Feb 2026 | Official leaderboard |
| 15 | GPT-4.1 mini | 11.8% | No compliance instruction, temperature 0 | Apr 2025 | Official leaderboard |
| 16 | | 12.6% | No compliance instruction, temperature 0 | Dec 2024 | Official leaderboard |
| 17 | GPT-4o-mini (snapshot unspecified) | 16.3% | No compliance instruction, temperature 0 | Official leaderboard | |
| 18 | Gemini 2.5 Pro (snapshot unspecified) | 21.1% | No compliance instruction, temperature 0 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.7 | 0.05% | No compliance instruction, temperature 0 | Apr 2026 | Official leaderboard |
| 2 | Claude 3.5 Haiku | 0.41% | No compliance instruction, temperature 0 | Oct 2024 | Official leaderboard |
| 3 | GPT-5.4 | 0.58% | No compliance instruction, temperature 0 | Mar 2026 | Official leaderboard |
| 4 | | 1.20% | No compliance instruction, temperature 0 | Nov 2024 | Official leaderboard |
| 5 | Claude Haiku 4.5 | 1.22% | No compliance instruction, temperature 0 | Oct 2025 | Official leaderboard |
| 6 | GPT-5.4 Mini | 1.42% | No compliance instruction, temperature 0 | Mar 2026 | Official leaderboard |
| 7 | | 1.96% | No compliance instruction, temperature 0 | Mar 2025 | Official leaderboard |
| 8 | Claude Sonnet 4.6 | 2.47% | No compliance instruction, temperature 0 | Feb 2026 | Official leaderboard |
| 9 | | 2.89% | No compliance instruction, temperature 0 | Apr 2025 | Official leaderboard |
| 10 | | 2.91% | No compliance instruction, temperature 0 | Sep 2025 | Official leaderboard |
| 11 | | 4.69% | No compliance instruction, temperature 0 | Mar 2025 | Official leaderboard |
| 12 | | 5.83% | No compliance instruction, temperature 0 | Dec 2025 | Official leaderboard |
| 13 | | 8.58% | No compliance instruction, temperature 0 | Apr 2025 | Official leaderboard |
| 14 | | 10.1% | No compliance instruction, temperature 0 | Feb 2026 | Official leaderboard |
| 15 | GPT-4.1 mini | 11.8% | No compliance instruction, temperature 0 | Apr 2025 | Official leaderboard |
| 16 | | 12.6% | No compliance instruction, temperature 0 | Dec 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The HireWatch paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official HireWatch leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Claude Opus 4.7. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (18 entries).
- Pass Models scored 16 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Claude Opus 4.7.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 16 rows for models we track and 2 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.