Cost-Effective Automated Judging of Natural-Language Mathematical Proofs
arXiv:2608.00004v1 Announce Type: new Abstract: Grading natural-language mathematical proofs is a recurring cost in evaluating math-reasoning systems, and frontier LLM judges are expensive. We ask whether cheap open-weight models can serve as reliable judges given a candidate proof, a ground-truth proof, and a human-grading rubric. On a 200-instance validation sample of IMO-GradingBench, three cheap judges (GPT-OSS 120B, DeepSeek-V4 Flash, Gemma-4 31B) agree with human pass/fail decisions at rates statistically indistinguishable from Claude Opus 4.7 and Gemini 3.1 Pro, at up to $100\times$ lower cost. We had expected a majority vote of the three to be the best budget option; it matched the frontier but did not improve on its strongest member. Extending to the full 1000-instance benchmark and exploring consensus rules, we found that requiring unanimous agreement (all-three-pass) reaches the highest pass-agreement and precision and, on four replicate runs, the smallest run-to-run spread. The headline finding is that cheap judges are competitive with the frontier at one to two orders of magnitude lower cost; as a deployable default we recommend all-three-pass, with the caveat that this rule was identified post-hoc and warrants independent replication.
-->
[Submitted on 29 May 2026]
Title:Cost-Effective Automated Judging of Natural-Language Mathematical Proofs
View a PDF of the paper titled Cost-Effective Automated Judging of Natural-Language Mathematical Proofs, by Benjamin Grayzel
View PDF HTML (experimental)
Abstract:Grading natural-language mathematical proofs is a recurring cost in evaluating math-reasoning systems, and frontier LLM judges are expensive. We ask whether cheap open-weight models can serve as reliable judges given a candidate proof, a ground-truth proof, and a human-grading rubric. On a 200-instance validation sample of IMO-GradingBench, three cheap judges (GPT-OSS 120B, DeepSeek-V4 Flash, Gemma-4 31B) agree with human pass/fail decisions at rates statistically indistinguishable from Claude Opus 4.7 and Gemini 3.1 Pro, at up to $100\times$ lower cost. We had expected a majority vote of the three to be the best budget option; it matched the frontier but did not improve on its strongest member. Extending to the full 1000-instance benchmark and exploring consensus rules, we found that requiring unanimous agreement (all-three-pass) reaches the highest pass-agreement and precision and, on four replicate runs, the smallest run-to-run spread. The headline finding is that cheap judges are competitive with the frontier at one to two orders of magnitude lower cost; as a deployable default we recommend all-three-pass, with the caveat that this rule was identified post-hoc and warrants independent replication.
Comments: 7 pages, 5 figures, 4 tables
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2608.00004 [cs.CL]
(or arXiv:2608.00004v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.00004
arXiv-issued DOI via DataCite
Submission history
From: Benjamin Grayzel [view email] [v1] Fri, 29 May 2026 17:22:57 UTC (250 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Cost-Effective Automated Judging of Natural-Language Mathematical Proofs, by Benjamin Grayzel
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-08
Change to browse by:
cs cs.AI cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)