CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Angular
Communication
Gaussian
Dynamics
Quantization
Precision
Electron
Interference
Simulation
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Communication
Geometry
Analysis
Index
LaTeX
Python
SymPy
Jupyter
English
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Optics
Channels
Optimization
Probability
Calculus
Linear
Simulation
Interference
Inequality
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Algebra
Statistics
Channels
Thermodynamics
Electron
Communication
Analysis
Geometry
Localization
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
AI
Chemistry
Chemical Safety
+12
Engineering
Pharmacology
Biochemistry
Accuracy
Calibration
Annotation
Contracts
Training
AI Safety
Organic Chemistry
Analytical Chemistry
Chemical Engineering
Pasiflora AI has immediate openings for Chemical AI Safety Annotators & Subject Matter Experts to evaluate AI-generated responses in chemistry and chemical-safety scenarios.
AI
Benchmarking
Reasoning
+12
Physics
Chemistry
Biology
Genetics
Neuroscience
Mathematics
Economics
Geology
Geophysics
Consistency
Analysis
Communication
Truelancer AI is looking for exceptional domain experts, researchers, and PhDs to contribute to an advanced AI Benchmarking Project.
AI
Reasoning
Literature
+11
Mechanical Systems
Interpretation
Biology
Research
English
Training
Make
Flexible
Life Sciences
Experimental Design
Data Interpretation
Models blur the line between what's established, what's contested, and what's simply made up in the life sciences, and they cite papers that don't exist.
Mathematics
Reasoning
AI
+8
Writing
LaTeX
English
Training
Make
Flexible
Mathematical Reasoning
Applied Mathematics
Frontier models still fail at rigorous multi-step mathematics: invalid derivations, unjustified leaps, and confidently wrong final answers. Automated checks can't grade a proof. You can.
Physics
AI
Reasoning
+8
Mechanics
Thermodynamics
Research
English
Training
Make
Flexible
Graduate-Level Physics
Models can recite physics and still get it wrong: dimensional errors, misapplied approximations, and derivations that skip the step where the physics actually happens.
Models routinely propose impossible mechanisms, unsafe procedures, and syntheses that no bench chemist would attempt. As a Chemist you'll evaluate AI chemical reasoning, catch what's wrong or unsafe, and write the answers a trained chemist would give.
Research
Engineering
Command Line
+12
Geophysics
Geology
AI
Python
Shell Scripting
Analysis
Modeling
Forecasting
Transformations
Accuracy
Metadata
Hydrology
We are seeking Earth Sciences experts to develop realistic, terminal-based scientific tasks for Terminal Bench Science. You will create computational workflows involving environmental data, climate systems, atmospheric processes, geophysics, oceanography, geology, and related…
AI
Audit
Training
+12
Reasoning
Physics
Accuracy
Logic
Engineering
English
Monday.com
Licensing
Red Teaming
Annotation
Writing
Go
Sovrano AI builds evaluation and training data for frontier AI labs, and this panel audits nuclear and radiological answers specifically. Each task gives you one user request and the answers three different models produced for it.
Research
Microsoft Teams
AI
+12
Training
MATCH
Writing
Analysis
Interpretation
Statistics
Communication
Reasoning
Biology
Chemistry
Physics
Astronomy
The research teams behind the best-known AI models come to Mercor for scientific judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
The research teams behind the best-known AI models come to Mercor for mathematical judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
The research teams behind the best-known AI models come to Mercor for physics judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
Chemistry
Research
Microsoft Teams
+11
AI
Training
MATCH
Writing
Mechanical Systems
Flask
Communication
Reasoning
AI Training
Computational Research
Written communication
The research teams behind the best-known AI models come to Mercor for chemistry judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
The research teams behind the best-known AI models come to Mercor for biotechnology judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
The research teams behind the best-known AI models come to Mercor for biology judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
We're looking for professionals with hands-on, real-world experience in specialized applications. Application Expertise and Access You must already have MATLAB installed/available on your own PC running Windows, and be able to open it today.
Biology
AI
GenAI
+12
Templates
Training
Research
Engineering
Microsoft Teams
Reasoning
CRISPR
Editing
Rubrics
Optimization
Genetics
Biochemistry
Join a leading AI lab's cutting-edge GenAI team to be at the core of the AI revolution, where your expertise fuels the development of the most advanced AI models. 1.
Biochemistry
Accuracy
Reasoning
+12
Mathematics
Mechanical Systems
Genetics
Interpretation
AI
Training
Biology
Chemistry
Pharmacology
English
Research
Teaching
In this hourly, remote contractor role, you will work as a Biochemistry Expert (SME) to review AI-generated biochemistry content and/or create high-quality biochemistry reference content, evaluating scientific accuracy, reasoning quality, terminology, and step-by-step…
AI
Audit
Training
+7
Physics
Licensing
Data Services
Nuclear Physics
Radiation Safety
Professional Experience
Red Teaming
## Description SME Careers is assembling a small panel of nuclear and radiological professionals to audit how AI models respond to sensitive questions in the field. Each task gives you a user request and the answers three different models gave to it.
Schedule: 10-15+ hours a week, Fully Flexible (Can accommodate working after hours/weekends) micro1 is engaging Physics Experts (PhD / Postdoc) to contribute deep scientific knowledge and problem-solving skills to a high-impact customer project.
