Models

t1

t11

a6

s1

M4

M1

bz3

K139

K171

StepSearch-3B-Instruct

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-domestic_fleecy_caribou

StepSearch-7B-Instruct

qwen3-8B-sft-mix-v20250921

SFT_Advanced_Risk_Situation_Aware_llama

FlashResearch-4B-Thinking

Qwen3-0.6B-Gensyn-Swarm-lively_fishy_wallaby

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-majestic_shrewd_salmon

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-burrowing_freckled_ferret

run1014-local-reasoning-baseline_lr1e-5_strict_F1_strictA2-step99

Hypa_Llama3.1-8b-SFT-2025-10-25-16bit

step_81_watson_qwen3_4b_watson_final_start_from_step_29_watson

Qwen3-1.7B_hh_helpful

Llama-3.2-3B_hh_harmful

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-pesty_leaping_beaver

alif-3b-fp16

task-17-microsoft-Phi-4-mini-instruct

affine-tobetop1

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-scavenging_lumbering_cod

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-rabid_grazing_antelope

qwen2.5_coder_3b_sqlfuse_probgate_only_answerable_delimeters_eos

cot-sft-model

SFT-Biomistral-7B-New

Biawak-8B-Base

HereticFT

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-beaked_slow_cat

qwen3-4b-thinking-rl-ckpt60

Qwen2.5-7B-Instruct-s1-pseudocode

ColdStart-Qwen2.5-14B

Qwen3-14B-Gemini-3-Pro-Preview-High-Reasoning-Distill

qwen3_0-6B_adversarial_1

qwen3_4b_sft_final

qwen3_0-6B_adversarial_3