MathNet-RAG - Embedding Retrieval: leaderboard
MathNet-RAG (2026) gives 35 Olympiad problems, each paired by experts with a related problem, and human experts grade the solutions. Accuracy when the model also gets one related problem and its solution found by an embedding retriever, in percent; higher is better.
Metric: on MathNet-RAG, 35 Olympiad problems each paired by experts with a related problem, graded by human experts; accuracy (%) with one related problem and its official solution retrieved by gemini-embedding-001; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 92.9 | #123 |
| 2 | DeepSeek V3.2 Speciale | 89.5 | #277 |
| 3 | Grok 4.1 Fast | 83.8 | #431 |
| 4 | GPT-5 | 75.2 | #185 |
| 5 | Claude Opus 4.5 | 55.5 | #165 |
| 6 | OLMo 3 32B (Thinking) | 54.6 | |
| 7 | Phi-4-reasoning-plus | 14.3 | #2288 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mathnet-rag-embedding-retrieval · How It Works · Data refreshed daily, snapshot 2026-11-22.