PsychEthicsBench
Models answer multiple-choice questions and respond to scenarios under Australian psychology and psychiatry ethics guidelines. Graders check responses against professional standards.
The authors tested 14 models. Four independent teams submitted workshop systems using the same question pool. The two grading methods ranked different teams first on free responses.
- Released
- January 2026
- Kind
- Wellbeing and sycophancy
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Risk
- Specialized advice
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Occupations
- Life, physical and social science, Healthcare practitioners and technical
- In views
- Biology and medicine, Content safety
- Strongest model tested
-
Llama 3-8B #206 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
Meditron3-14B tops the leaderboard with 82% Qwen2.5-14B leads with 75.6% among models released by September 2024
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. The best model we track is Qwen2.5-14B, at 75.6%. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2024, 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 Meditron3-14B Global 82%
- 2 Baichuan-m1-14B Global 78.6%
- 3 HuatuoGPT-7B Global 75.6%
- 4
Qwen2.5-14B Global 75.6%
- 5 Crispers-14B Global 74.5%
- 6 Meditron3-7B Global 72.2%
- 7
Qwen2.5-7B Global 70.1%
- 8 Med42-Llama-8B Global 68.2%
- 9 Crispers-7B Global 66.6%
- 10
Llama 3-8B Global 64.8%
- 11
Llama 2-13B Global 56.9%
- 12 EmoLlama-13B Global 30.6%
- 13 Mentallama-13B Global 27.1%
- 14 SQPsychLLM-8B Global 11.6%
Source: The PsychEthicsBench paper
- 1
Qwen2.5-14B Global 75.6%
- 2
Qwen2.5-7B Global 70.1%
- 3
Llama 3-8B Global 64.8%
- 4
Llama 2-13B Global 56.9%
Source: The PsychEthicsBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Meditron3-14B | 82% | Global | Official leaderboard | |
| 2 | Baichuan-m1-14B | 78.6% | Global | Official leaderboard | |
| 3 | HuatuoGPT-7B | 75.6% | Global | Official leaderboard | |
| 4 | | 75.6% | Global | Sep 2024 | Official leaderboard |
| 5 | Crispers-14B | 74.5% | Global | Official leaderboard | |
| 6 | Meditron3-7B | 72.2% | Global | Official leaderboard | |
| 7 | | 70.1% | Global | Sep 2024 | Official leaderboard |
| 8 | Med42-Llama-8B | 68.2% | Global | Official leaderboard | |
| 9 | Crispers-7B | 66.6% | Global | Official leaderboard | |
| 10 | | 64.8% | Global | Apr 2024 | Official leaderboard |
| 11 | | 56.9% | Global | Jul 2023 | Official leaderboard |
| 12 | EmoLlama-13B | 30.6% | Global | Official leaderboard | |
| 13 | Mentallama-13B | 27.1% | Global | Official leaderboard | |
| 14 | SQPsychLLM-8B | 11.6% | Global | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 75.6% | Global | Sep 2024 | Official leaderboard |
| 2 | | 70.1% | Global | Sep 2024 | Official leaderboard |
| 3 | | 64.8% | Global | Apr 2024 | Official leaderboard |
| 4 | | 56.9% | Global | Jul 2023 | 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 PsychEthicsBench 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 PsychEthicsBench 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 Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6%
- Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in September 2024, for Qwen2.5-14B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (14 entries).
- Pass Models scored 4 models we track, plus 10 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in September 2024, for Qwen2.5-14B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3-8B (#206).
- Pass Headroom The best is 75.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 4 rows for models we track and 10 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.