OpenDeepThink 用 Bradley-Terry 聚合解决了并行推理的候选选择难题，做推理扩展的开发者可以直接复现，效果显著且无需调参。
OpenDeepThink 是一种基于种群的测试时计算扩展框架，通过成对 Bradley-Terry 比较选择最佳推理候选，解决了并行采样中的选择瓶颈。每次迭代中，LLM 对随机候选对进行评判并聚合为全局排名，保留顶部候选并变异前四分之三，丢弃底部四分之一。在 Codeforces 上，Gemini 3.1 Pro 的 Elo 评分在 8 轮 LLM 调用（约 27 分钟）内提升 405 分。该方法跨弱强模型无需重新调参，在 HLE 基准上，增益集中在客观可验证领域，主观领域则出现逆转。同时发布了 CF-73 数据集，包含 73 道专家评级的 Codeforces 问题。
OpenDeepThink: Parallel Reasoning via Bradley--Terry Aggregation
Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling multiple candidates in parallel is straightforward, but introduces a selection bottleneck: choosing the best candidate without a ground-truth verifier, since pointwise LLM judging is noisy and biased. To address this, we introduce OpenDeepThink, a population-based test-time compute framework that selects via pairwise Bradley-Terry comparison. Each generation, the LLM judges random pairs of candidates and aggregates votes via Bradley-Terry into a global ranking; top-ranked candidates are preserved and the top three quarters are mutated using the natural-language critiques produced during comparison; the bottom quarter is discarded. OpenDeepThink raises Gemini 3.1 Pro's effective Codeforces Elo by +405 points in eight sequential LLM-call rounds (~27 minutes wall-clock). The pipeline transfers across weaker and stronger models without retuning, and on the multi-domain HLE benchmark, gains appear concentrated in objectively verifiable domains and reverse in subjective ones. We release CF-73, a curated set of 73 expert-rated Codeforces problems with International Grandmaster annotation and 99% local-evaluation agreement against the official verdict.