New AI Models (Last 6 Months) — Page 44

SympQwen-0.5B

OpenSWE-72B

Qwen3-1.7B-SFT-s1K-lr2eneg05

dpo-qwen3_4b-cot-merged_v260302-112329

SFT_Qwen2.5-3B-Instruct_MATH

qwen-0.6b-job-matcher-student

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_0

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_2

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_1

longer_response-Qwen3-0.6B-baseline_all_tokens-seed_2

general_reward-Qwen3-0.6B-baseline_cot_only-seed_0

tmax-qwen3-4b-sft-20260316-100k-asst-loss

general_reward-Qwen3-0.6B-baseline_cot_only-seed_1

tmax-qwen3-4b-sft-20260316-100k-asst-loss

qwen3lora

goedel_prover_v2_8b_reviewer_finetuned_2048_num_samples

aai-accountant-tt133-v1.0

confidence-Qwen3-0.6B-OURS_self-seed_2

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_0

confidence-Qwen3-0.6B-baseline_all_tokens-seed_2

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_1

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_2

tau-max-ds-sft

Magistral-Small-2509-ultra-uncensored-heretic-v2

Qwen2.5-0.5B_debiased

Llama-3.2-1B-Instruct_SFT_sciencev00.04

Qwen3-4B-Base-ftjob-0511c5edc14e

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_10_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

Artemis-Coder-1.5B

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_10_1p0_0p0_1p0_grpo_42_rule

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_0

phi-1.5-distill-Proposed_MLP_L2_Beta2.0-merged

phi-1.5-distill-Ablation_High_Beta_2.5-merged

olympiad-curated-qwen3-4b-nemotron-5ep

Qwen2.5-3B-Instruct-C_M_T_CT

student_feedback_v1_Qwen3-4B-Base

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e0_1p0_0p0_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_dr_grpo_42_rule