Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling
TB-MathModel is a terminal-style benchmark built from 18 real CUMCM and MCM contest problems (2023–2025), where agents receive full problem statements and attachments in a containerized environment and return one structured JSON artifact.
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face
- Discovery linkHugging Face
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
TB-MathModel is a terminal-style benchmark built from 18 real CUMCM and MCM contest problems (2023–2025), where agents receive full problem statements and attachments in a containerized environment and return one structured JSON artifact. Scoring checks the numeric core of the final answer against a reproduction of an Outstanding-award paper using direction-aware, one-sided scoring, with feasibility enforced by a programmatic gate and 624 Lean 4 obligations. Across seven multimodal entries, the best reaches a multi-reference O-Eval of 64.58%, while a $2.54 open model reaches 59.81% at about 1/100 the cost. The source describes the benchmark as a way to measure long-horizon modeling competence and collect agent trajectories.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the full paper was not reviewed beyond the supplied text, and results are limited to 18 contest-derived problems.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; the full paper was not reviewed beyond the supplied text, and results are limited to 18 contest-derived problems.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Scoring checks the numeric core of each final answer against a reproduction of an Outstanding-award paper, with one-sided scoring that does not penalize beating the anchor.
Source: Hugging Face ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseEach task is scored against a panel of human outstanding papers rather than a single reference, with 94 reference answers in total.
Source: Hugging Face ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseFeasibility is checked by a programmatic gate over six decidable invariant forms plus 624 Lean 4 kernel-checked obligations, with a hard gate zeroing infeasible answers.
Source: Hugging Face ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseThe strongest entry, GPT-6 Astra, reaches a multi-reference O-Eval of 64.58%, while a $2.54 open model holds 59.81% at 1/100 the cost.
Source: Hugging Face ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the full paper was not reviewed beyond the supplied text, and results are limited to 18 contest-derived problems.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
Mathematical modeling is a step beyond well-posed problem solving, and existing evaluations either score solver fragments or use LLM judges. A checkable benchmark with feasibility verification could give a more reproducible signal of long-horizon modeling competence.
Limits and open questions
Source claims not independently checked; the full paper was not reviewed beyond the supplied text, and results are limited to 18 contest-derived problems.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →