Models

dpo-llama3.2-gspo-original-400

qwen_omi2_step100

short_paper_llama_llama3.1-8b_train_sft_all_train_no_think

short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think

qwen3-4b-pokergpt-o3-sft-lora

struct-v6

VerdictAI-8b-V2

rc_qwen3_4b_thinking_2507_proof-20260112-064952

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

random-v7

llama-3.3-70B-Instruct-en-tt

c66-h12

Qwen3-4B-Instruct-DSGym-SFT-2K

qwen25-coder-7b-swe-gym-2291i-no-docstring-gen-5e-0-00005lr-bs16-bf16

struct-v8

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_96

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_192

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

StudyAiv17

agentic-sokoban-NonMarkov_qwen3-4B-5e-6_gt-SFT_4k

qwen3_1.7b_easy_rl_ours_adv_fixed_no_norm

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_592

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_288

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_384

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296

qwen3_1.7b_sudoku_one_act_new

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

Qwen3-0.6B-Gensyn-Swarm-furry_zealous_raccoon

Laser-L8192-1.5B

general

Qwen2.5-0.5B-Instruct-sft-77

llama-1b-sft-tldr

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

64b_RL_DAPO

rl-4b-arc-abstractions-judge-norm-nothink-deltarerun-step210-0116

dyck-test

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