WebWorld-32B
Assistant_Pepe_32B
hivemind-32b-preview
Qwen3-32B
DeepSWE-Preview
UIGEN-FX-Agentic-32B
Qwen3-Nemotron-32B-GenRM-Principle
Qwen3-Nemotron-32B-RLBFF
SafeMed-R1
SERA-32B
SERA-32B-GA
PsychAgent-Qwen3-32B
M3-Agent-Control
Nemotron-Terminal-32B
DataChef-32B
Zhi-Create-Qwen3-32B
Affine-GRP5-5CUNn9DYCzYVgAY7npqgRshVnvj2Bs6EXkeFhCTJ4Yj41Hmu
Goedel-Prover-V2-32B
shuttle-3.5
XBai-o4
Cybus-Qwen3-32B-v2-agentic
FrogBoss-32B-2510
T-pro-it-2.1
Qwen-SEA-LION-v4-32B-IT
Qwen3-Swallow-32B-RL-v0.2
affine-5EtPj7mKQ6arxx8KW3GFTWBzTBia1DyM2vDU1rpNPsRHUk1B
affine-5Gq9oYPn5qbe8yUViJagePXHio9mmd8cfJZQ4HG8k27UUckK
Qwen3-32B-abliterated
affine-28-5CSriXZUwkoqdKBF4kqgRPBgrRiyPbLEo6TBaR3rW3u5qo4T
affine-5FqNniTYPXPDVEdchUgthfwT66yp4uDphJw7ArXKS2MhhCs3
g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B
g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B
g1_timeout_e1_gpt_long_thinking_tacc-Qwen3-32B
g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B
test
GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_6.0_Qwen3-32B
Qwen3-Swallow-32B-SFT-v0.2
T-pro-it-2.0
affine-ana20-1-5F9pyrPr9DfYvaR7Vy4Tjg6EgQ75GEPwxN4yrSAaDqBMe9up
affine-ana13-1-5EHEbq3gKeDz9rpQejXpHrG2T8FNn5u8UxWYKHAq83Mg7yqY
SA-SWE-32B