# Anthropic STEM Professor Bench (STEM Professor Bench)

> Anthropic's internal set of unpublished research problems written by professional scientists, each about a month of research work, mostly in theoretical physics; BenchLM stores the 64-problem subset.

Canonical page: https://benchlm.ai/benchmarks/stemprofessorbench

- Category: [Reasoning](/reasoning)
- Last updated: November 11, 2026

## About STEM Professor Bench

- Year: 2026
- Tasks: 64 research problems
- Format: Mean score over up to nine attempts
- Difficulty: Research-level science
- Paper: [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf)

Each model works as a single agent with Python, bash and a file editor within each author's limits, with a fixed arXiv index up to December 1, 2025 on 58 problems. Claude Opus 5 grades 56 problems against answer keys or rubrics; the rest use author-written checkers. Values are read from the labeled bars of Figure 8.9.A. Internal, so display-only.

STEM Professor Bench is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (3 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Fable 5.2](/models/claude-fable-5-2) | Anthropic | 61.8% |
| 2 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 53.7% |
| 3 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 29.9% |

## FAQ

### What does STEM Professor Bench measure?

Anthropic's internal set of unpublished research problems written by professional scientists, each about a month of research work, mostly in theoretical physics; BenchLM stores the 64-problem subset.

### Which model scores highest on STEM Professor Bench?

Claude Fable 5.2 by Anthropic currently leads with a score of 61.8% on STEM Professor Bench.

### How many models are evaluated on STEM Professor Bench?

3 AI models have published results on STEM Professor Bench in the BenchLM catalog.

### Does STEM Professor Bench affect BenchLM's overall score?

Not directly. STEM Professor Bench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on STEM Professor Bench

- [Claude Fable 5.2 vs Claude Opus 5.5](/compare/claude-fable-5-2-vs-claude-opus-5-5)
- [Claude Opus 5.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-opus-5-5)