pith. sign in

LiveCodeBench 05/23-05/24 subset has 511 problems released between May 2023 and May 2024, whereas the 06/24-01/25 subset has 369 problems released between May 2024 and Jan

LiveCodeBench: a benchmark of real-world programming tasks that evaluate a model’s ability to generate, execute, verify, iteratively repair solutions using unit-test feedback · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

citation-role summary

dataset 1

citation-polarity summary

use dataset 1

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

dataset 1

polarities

use dataset 1

representative citing papers

OpenThoughts: Data Recipes for Reasoning Models

cs.LG · 2025-06-04 · conditional · novelty 7.0

OpenThoughts3-7B, trained on a 1.2M-example public dataset via systematic pipeline optimizations, achieves 53% on AIME 2025, 51% on LiveCodeBench, and 54% on GPQA Diamond.

citing papers explorer

Showing 1 of 1 citing paper.

  • OpenThoughts: Data Recipes for Reasoning Models cs.LG · 2025-06-04 · conditional · none · ref 8

    OpenThoughts3-7B, trained on a 1.2M-example public dataset via systematic pipeline optimizations, achieves 53% on AIME 2025, 51% on LiveCodeBench, and 54% on GPQA Diamond.