New AI Models (Last Year) — Page 482

ee_gol_grp_f1_form_multi

Llama-3.1-8B-counterfactual-extended-facts-first-third

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E3-S73

teacher_qwen3_1p7b_gpqa_cot

SOR-ColdBrew-12B-Base-Test3

qwen3-0.6b-lora-256-256-lr-0.0001-bs-256

fgrpo-gspo-cl3e3-qwen25-math-1.5b-step751

llama31-8b-gtow-lora-v2

code_think_x_qwen3_4b_base_sft

Llama-3.1-8B-weird-german-city-names-last-third

retail-banking-Qwen3-4B-Instruct-2507

code_think_8_qwen3_4b_instruct_sft

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step821-aime24-40pct

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S3407

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S9

fgrpo-gspo-cl3e3-drgrpo-llama32-3b-math-step921

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step741-aime24-38pct

llama31-8b-gtow-lora-v3

llama31-8b-hh-rlhf-aligned

general_knowledge_model

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9

cs224r-rloo

Llama-3.2-3B-GSPO-cl3e3-DrGRPO-Step561-BestPass1-DeepScaleR-AIME24

multilingual_model

unsup-Qwen3-8B-datav3-cpt

Qwen2.5-Coder-PERTA-LEETCODE-1.5B-Base

mhm_ties__merge_experiments_math_think_11_ties_density_0p10

multilingual_model

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step1061-aime24-43pct

group_model

science_4bmix_m32-3dded240-not_easy_1e-5_1200

qwen2.5-7B-it-dpo-abstention-high-lr

CEEH_7B_ME

qwen3_4b_clipcov_baseline_solver_v2

qwen3_4b_klcov_baseline_solver_v4

bodh-merged-v9

Qwen2.5-7B-turkish-culture-veri_2_half_epoch_

Qwen3-4B-TL-SynthDolly-r16alpha128-E5-S3407

Qwen3-4B-ZH-SynthDolly-r16alpha128-E5-S73

Qwen3-4B-ZH-SynthDolly-r16alpha128-E8-S73

qwen3-4B_finetuned

Qwen3-4B-Claude-Sonnet-4-Reasoning-Distill-Heretic-Abliterated-Heretic-Abliterated