Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

• URL: http://arxiv.org/abs/2605.13301v1
• Date: Wed, 13 May 2026 10:13:26 GMT
• Title: Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
• Abstract summary: We introduce a simple and unified recipe for converting a post-trained reasoning backbone into a rigorous olympiad-level solver.<n>We train a 30B-A3B backbone with SFT on around 340K sub-8K-token trajectories followed by 200 RL steps.<n>The resulting model, SU-01, supports stable reasoning on difficult problems with trajectories exceeding 100K tokens.
• Score: 108.48818215929494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with several systems now reaching gold-medal-level performance on International Mathematical Olympiad (IMO) and International Physics Olympiad (IPhO) problems. In this paper, we introduce a simple and unified recipe for converting a post-trained reasoning backbone into a rigorous olympiad-level solver. The recipe first uses a reverse-perplexity curriculum for SFT to instill rigorous proof-search and self-checking behaviors, then scales these behaviors through a two-stage RL pipeline that progresses from RL with verifiable rewards to more delicate proof-level RL, and finally boosts solving performance with test-time scaling. Applying this recipe, we train a 30B-A3B backbone with SFT on around 340K sub-8K-token trajectories followed by 200 RL steps. The resulting model, SU-01, supports stable reasoning on difficult problems with trajectories exceeding 100K tokens, while achieving gold-medal-level performance on mathematical and physical olympiad competitions, including IMO 2025/USAMO 2026 and IPhO 2024/2025. It also demonstrates strong generalization of scientific reasoning to domains beyond mathematics and physics.

Related papers

• Post-Training Language Models for Gold-Medal Performance in Coding Competitions [70.8192632995446]
  We present an end-to-end specialization pipeline combining large-scale problem curation, synthetic reasoning traces, supervised fine-tuning, and reinforcement learning.<n>Using 22,000 curated problems, we train Nemotron-3-Nano-CC with SFT and RL and Nemotron-3-Ultra-CC (550B-A55B) with SFT alone.<n>On IOI 2025, Nano-CC improves from 130 points to 291 after post-training and to 468 with GenCorrect, exceeding the gold threshold of 438.3 while Ultra-CC reaches 502.
  arXiv  Detail & Related papers  (2026-09-02T17:33:37Z)
• ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions [20.614899115950156]
  ScienceArena is an olympiad-style benchmark from thirteen public science competitions in physics, chemistry, and biology.<n>We build ScienceArena through an expert-audited digitization pipeline that converts official exams, figures, solutions, and rubrics into structured items verified by olympiad medalists.<n> Medalist notes show that failures often stem from visual grounding, structure fidelity, and global problem control rather than missing terminology.
  arXiv  Detail & Related papers  (2026-08-31T09:52:29Z)
• QED-Nano: Teaching a Tiny Model to Prove Hard Theorems [34.119608370222245]
  We build QED-Nano, a 4B model post-trained for Olympiad-level proofs.<n>We release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.
  arXiv  Detail & Related papers  (2026-04-06T17:44:25Z)
• Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation [114.31258597102926]
  Nemotron- Cascade 2 is an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities.<n>It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad.
  arXiv  Detail & Related papers  (2026-03-19T17:58:52Z)
• Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models [71.9060068259379]
  We propose cascaded domain-wise reinforcement learning to build general-purpose reasoning models.<n>Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6 Pro and silver-medal performance in the 2025 International Olympiad in Informatics (IOI)
  arXiv  Detail & Related papers  (2025-12-15T18:02:35Z)
• Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving [65.02106674311908]
  This paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning.<n>By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces.<n> Experiments show that Intern-S1-MO can obtain 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists.
  arXiv  Detail & Related papers  (2025-12-11T15:26:28Z)
• LOCA-R: Near-Perfect Performance on the Chinese Physics Olympiad 2025 [3.5580730009417016]
  We introduce LOCA-R (LOgical Chain Augmentation for Reasoning), an improved version of the LOCA framework adapted for complex reasoning.<n>LOCA-R achieves a near-perfect score of 313 out of 320 points, solidly surpassing the highest-scoring human competitor.
  arXiv  Detail & Related papers  (2025-11-13T17:20:46Z)
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model [100.86587937568832]
  Ring-1T is the first open-source, state-of-the-art thinking model with a trillion-scale parameter.<n>It features 1 trillion total parameters and activates approximately 50 billion per token.
  arXiv  Detail & Related papers  (2025-10-21T17:46:14Z)
• HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark? [53.76627321546095]
  HiPhO is the first benchmark dedicated to high school physics Olympiads with human-aligned evaluation.<n>It compiles 13 latest Olympiad exams from 2024-2025, spanning both international and regional competitions.<n>We assign gold, silver, and bronze medals to models based on official medal thresholds, thereby enabling direct comparison between (M)LLMs and human contestants.
  arXiv  Detail & Related papers  (2025-09-09T16:24:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.