Tool profile

open-thought/reasoning-gym

stable

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

gymlarge-language-modelsreinforcement-learning

Velocity score

0.26/ 10

[STARS]

1.4k

[FORKS]

119

[CONTRIBUTORS]

[LAST_COMMIT]

1mo ago

Score breakdown

607/ 1000

frameworks · open-thought/reasoning-gym

Velocity50%

Adoption30%

Maintenance15%

Community5%

[CODE_GROWTH]

707

[INSTALL_VEL]

496

[ACTIVITY]

390

[COMMUNITY_SIGNAL]

918

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).