mlsanityData to 7 Oct 2026

Towards Robust Mathematical Reasoning

arXiv 2511.01846 ↗First posted 3 Nov 2025cs.CL cs.AIcited by 67

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

Finding the right north-star metrics is highly critical for advancing the mathematical reasoning capabilities of foundation models, especially given that existing evaluations are either too easy or only focus on getting correct short answers. To address these issues, we present IMO-Bench, a suite of advanced reasoning benchmarks, vetted by a panel of top specialists and that specifically targets the level of the International Mathematical Olympiad (IMO), the most prestigious venue for young mathematicians. IMO-AnswerBench first tests models on 400 diverse Olympiad problems with verifiable short answers. IMO-Proof Bench is the next-level evaluation for proof-writing capabilities, which includes both basic and advanced IMO level problems as well as detailed grading guidelines to facilitate automatic grading. These benchmarks played a crucial role in our historic achievement of the gold-level performance at IMO 2025 with Gemini Deep Think (Luong and Lockhart, 2025). Our model achieved 80.0% on IMO-AnswerBench and 65.7% on the advanced IMO-Proof Bench, surpassing the best non-Gemini models by large margins of 6.9% and 42.4% respectively. We also showed that autograders built with Gemini reasoning correlate well with human evaluations and construct IMO-GradingBench, with 1000 human gradings on proofs, to enable further progress in automatic evaluation of long-form answers. We hope that IMO-Bench will help the community towards advancing robust mathematical reasoning and release it at https://imobench.github.io/.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 13 of its 30 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

13 of 30 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI7 Nov
  2. 2024Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models10 Oct
  3. 2024Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap29 Feb

Other references · 10

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2023Let's Verify Step by Stepcited by 3,598
  4. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  5. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  6. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 480
  7. 2021MiniF2F: a cross-system benchmark for formal Olympiad-level mathematicscited by 380
  8. 2025Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2cited by 95
  9. 2024HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematicscited by 32
  10. 2025Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 63.

67 papers.

Sort:

By area:

  1. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  2. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 502
  3. 2026Kimi K2.5: Visual Agentic Intelligencecited by 449
  4. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  5. 2026Qwen3.5-Omni Technical Reportcited by 146
  6. 2025DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoningcited by 84
  7. 2026Seed1.8 Model Card: Towards Generalized Real-World Agencycited by 47
  8. 2026LongCat-Flash-Thinking-2601 Technical Reportcited by 32
  9. 2026Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learningcited by 26
  10. 2026The Red Queen G"odel Machine: Co-Evolving Agents and Their Evaluatorscited by 16
  11. 2026AI co-mathematician: Accelerating mathematicians with agentic AIcited by 13
  12. 2026Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RLcited by 11
38 more
  1. 2026LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworkscited by 11
  2. 2026Self-Compacting Language Model Agentscited by 11
  3. 2026Automated Benchmark Auditing for AI Agents and Large Language Modelscited by 10
  4. 2026Scaling Self-Play with Self-Guidancecited by 9
  5. 2026Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Modelcited by 9
  6. 2026Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Modelscited by 8
  7. 2025P1: Mastering Physics Olympiads with Reinforcement Learningcited by 7
  8. 2026LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learningcited by 6
  9. 2026Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scalecited by 6
  10. 2026Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Modelscited by 5
  11. 2026MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrievalcited by 5
  12. 2026SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoningcited by 4
  13. 2026DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantizationcited by 4
  14. 2026FUSE: Ensembling Verifiers with Zero Labeled Datacited by 3
  15. 2026Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctnesscited by 3
  16. 2026Pseudo-Formalization for Automatic Proof Verificationcited by 3
  17. 2025Pessimistic Verification for Open Ended Math Questionscited by 2
  18. 2026K-EXAONE Technical Reportcited by 2
  19. 2026PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Lengthcited by 2
  20. 2026ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learningcited by 2
  21. 2026The Potential of CoT for Reasoning: A Closer Look at Trace Dynamicscited by 2
  22. 2026Do We Need Frontier Models to Verify Mathematical Proofs?cited by 2
  23. 2026QED-Nano: Teaching a Tiny Model to Prove Hard Theoremscited by 2
  24. 2026DASC: Decay-Aware State Compression for Hybrid Linear-Attention Servingcited by 2
  25. 2026Perfect score on IPhO 2025 theory by Gemini agentcited by 1
  26. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discoverycited by 1
  27. 2026MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysiscited by 1
  28. 2026VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Modelscited by 1
  29. 2026Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teamscited by 1
  30. 2026From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontiercited by 1
  31. 2026Cost-Effective Automated Judging of Natural-Language Mathematical Proofscited by 1
  32. 2026LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexingcited by 1
  33. 2026Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMscited by 0
  34. 2026Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Provingcited by 0
  35. 2026VAMPS: Visual-Assisted Mathematical Problem Solving Benchmarkcited by 0
  36. 2026ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatoricscited by 0
  37. 2026Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMscited by 0
  38. 2026Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofscited by 0

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025RIMO: An Easy-to-Evaluate, Hard-to-Solve Olympiad Benchmark for Advanced Mathematical Reasoning
  2. 2025AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
  3. 2025CombiGraph-Vis: A Curated Multimodal Olympiad Benchmark for Discrete Mathematical Reasoning
  4. 2025EEFSUVA: A New Mathematical Olympiad Benchmark
  5. 2025Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
  6. 2026Riemann-Bench: A Benchmark for Moonshot Mathematics
  7. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
  8. 2025UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models