Skip to main content

Teaching-over-Solving Diagnostic

A small tool for one question: is an LLM tutor as good at teaching as it is at solving?

A model that solves math problems well can still be a weak tutor. It may give away the answer, skip scaffolding, or ignore what the student already knows. If a benchmark folds everything into one "helpfulness" score, that difference disappears.

This diagnostic keeps the two apart. From per-task benchmark scores it computes:

  • Solve: the mean of solving-oriented tasks;
  • Teach: the mean of pedagogy-oriented tasks;
  • Gap = Teach − Solve: positive means relatively stronger at teaching.

Across a set of models it also reports how far each model's rank moves between the two views, the Pearson and Spearman correlations between Solve and Teach, and a leave-one-out range that shows how fragile those correlations are.

This is the companion tool for Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors (5th Workshop on NLP for Positive Impact, 2026, OpenReview).

Scope. This is a descriptive diagnostic on benchmark scores. It does not measure student learning. With few models, correlations are fragile, so read them together with the leave-one-out range.

Solve versus Teach on the public MathTutorBench leaderboard

Install

Python 3.10 or newer. No dependencies.

python -m pip install teaching-over-solving

This installs the tos-diagnostic command (teaching-over-solving also works) and the tos_diagnostic Python package. To work from source:

git clone https://github.com/Garyouki/teaching-over-solving.git
cd teaching-over-solving
python -m pip install -e ".[dev]"
python -m pytest

Reproduce the paper

tos-diagnostic paper --report report.md --svg scatter.svg

This uses the eight public MathTutorBench leaderboard models bundled with the package. It reproduces the paper's Table 1 composites, the Spearman correlation (0.690), the leave-one-out Pearson range (0.251–0.887), and the two rank shifts the paper describes:

  • LLaMA3.1-8B-Instruct rises from rank 7 on solving to rank 4 on teaching (gap +0.077).
  • Qwen2.5-Math-7B-Instruct falls from rank 4 to rank 8 (gap −0.452).

The exact Pearson correlation is 0.4217. The paper prints it as 0.421.

examples/paper_report.md shows the full report.

Diagnose your own tutor

MathTutorBench scores

Put one row per model in a CSV with the nine MathTutorBench task scores. The leaderboard's own column headers (for example Problem Solving or Scaffolding (Hard)) are recognized.

tos-diagnostic score my_models.csv --reference --report report.md --svg scatter.svg

--reference places your models next to the eight public models. Scores can be fractions (0.64) or percentages (64%).

Group MathTutorBench tasks
Solve problem solving, solution correctness, mistake location, mistake correction
Teach Socratic questioning, scaffolding win rate, pedagogy instruction-following win rate, scaffolding (hard), pedagogy instruction-following (hard)

The paper treats mistake location and mistake correction as solving tasks, because they test whether the model can find or repair the mathematical state of the problem.

Any other benchmark

Name the columns for each side:

tos-diagnostic score scores.csv --solve accuracy,final_answer \
    --teach scaffolding,guiding_questions,rigor

Use this for any benchmark that reports separate solving and teaching scores per model, including your own internal evaluations.

Missing scores stop the run by default. --allow-missing averages the scores that are present and marks those models in the report.

Python

from tos_diagnostic import diagnose, load_scores, with_reference

result = diagnose(with_reference(load_scores("my_models.csv")))
for m in result["models"]:
    print(m["model"], round(m["gap"], 3), m["solve_rank"], "->", m["teach_rank"])

Rubric agency density

The paper's second study counts how often tutoring-benchmark rubrics reward agency-preserving behavior, such as asking guiding questions or giving hints without revealing the next step. tos-diagnostic rubrics computes these densities from rubric items you have tagged:

tos-diagnostic rubrics examples/example_rubrics.jsonl

The keyword rules are transparent and replaceable. Reading TutorBench's raw rubric format, and matching the paper's Table 2 exactly, is not yet re-validated in this package. See docs/rubric_rules.md.

Limitations

  • Benchmark scores are not learning outcomes. A positive gap does not show that a tutor helps students learn more.
  • The public leaderboard has only eight models. Removing one model moves the Pearson correlation between 0.251 and 0.887.
  • Other task groupings are possible. The default grouping is a transparent choice, not a definitive taxonomy.
  • The diagnostic works on aggregate scores. It does not check answer disclosure turn by turn.

Data

src/tos_diagnostic/data/mathtutorbench_leaderboard.csv contains the public MathTutorBench leaderboard scores for eight models (Macina et al., EMNLP 2025). Please cite MathTutorBench when you use them.

Citation

@inproceedings{yao2026beyond,
  title     = {Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in {LLM} Tutors},
  author    = {Junyi Yao and Zihao Zheng and Baichuan Li},
  booktitle = {5th Workshop on NLP for Positive Impact},
  year      = {2026},
  url       = {https://openreview.net/forum?id=aZ1KTkxECP}
}

License

MIT. See LICENSE.

Metadata

Release files for teaching-over-solving 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for teaching-over-solving 0.1.2
File Size Uploaded Provenance Actions
teaching_over_solving-0.1.2.tar.gz 16.7 kB With provenance Details for teaching_over_solving-0.1.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for teaching-over-solving 0.1.2
File Interpreter ABI Platform Actions
teaching_over_solving-0.1.2-py3-none-any.whl Python 3 none any Details for teaching_over_solving-0.1.2-py3-none-any.whl

Total release size: 34.0 kB

Release files / teaching_over_solving-0.1.2.tar.gz

Download URL teaching_over_solving-0.1.2.tar.gz
Size 16.7 kB
Tags Source
SHA-256 checksum
How to use checksums
373b8189c8da139ef0a4c68df77cd0e7ea7ec4158c59792f730a69932b043a0c
BLAKE2b-256 checksum
How to use checksums
55d5de5e815bafdab69ae8e4d9015856b1e3e7d564aa8a27842cfa3d54a34130
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.

Transparency log

Release files / teaching_over_solving-0.1.2-py3-none-any.whl

Download URL teaching_over_solving-0.1.2-py3-none-any.whl
Size 17.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3ea678cc8697b3c5da5428276735fa5fbe9bbb197bfecf9a7ce1ed9e8997eba9
BLAKE2b-256 checksum
How to use checksums
7655c0cf920ba6d3050d038f969a710e4a57a8cb17e914452376d0587e1f9ec9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.

Transparency log

Security for teaching-over-solving 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for teaching_over_solving-0.1.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page