ParaTempo: Efficient Parallel Reasoning via Temporal Confidence
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime-2026
ParaTempo (GPT-OSS-20B)
#26
Accuracy: 86.7
multiple-choice-question-answering-mcqa-on-gpqa-diamond
ParaTempo (Qwen3.5-35B-A3B)
#36
Accuracy: 85.4
Rank counts only results with a code link.