SABER-Math: leaderboard
Metric: Overall nDCG@10 (0-100) with exponential gain, printed 0 to 1 and scaled by 100: each competition or olympiad problem query reranks its own pool of 150 candidate problems, graded 0 to 5 by Bradley-Terry fits of GPT-OSS-120B pairwise relevance judgments over a 20-round Swiss tournament; every system at its default configuration and task instruction, all 1000 queries, statement-full setting (the query is a problem statement, each document a problem with its solution); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 43 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-Embedding-8B | 61.1 |
| 2 | Qwen3-Embedding-0.6B | 57.5 |
Interactive version: theaggregate.ai/benchmark?slug=saber-math · How It Works · Data refreshed daily, snapshot 2026-09-29.