New AI Models (Last Year) — Page 88

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

Llama-3.2-1B-Instruct-C_M_T_CT_CE_CM

P2-split3_prob_Qwen3-4B-Base_0312-01

konkani-qwen2-1.5b

SympQwen-0.5B

gemma2b-webxr-showroom-v2

Akkadian-Pretrain-Qwen3-4B-Instruct-2507

qwen3-4b-jee-final

Qwen3-1.7B-SFT-s1K-lr2eneg05

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_0

OpenRS-GRPO-S

slf-dstl_Q2.5-1.5B-It_science_SFT

medical-chatbot-base

Qwen2-0.5B-Instruct

Merging_Qwen2.5-1.5B-Instruct_MedQA_lr1e-05_mb2_ga128_n2048_seed42

frozen-lake-agent-001

GRPO_KL_Qwen2.5-3B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

Qwen3-0.6B-Base-CPT-Math

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

Gamia-pygame-v1

general_reward-Qwen3-0.6B-OURS_self-seed_2

confidence-Qwen3-0.6B-baseline_all_tokens-seed_2

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_1

general_reward-Qwen3-0.6B-OURS_llama-seed_2

HiTOP-QWEN4B_4bit

Qwen2.5-0.5B_debiased

arbor-treesearch-3b

Llama-3.2-1B-Instruct_SFT_sciencev00.01

Qwen3-4B-Base-ftjob-0511c5edc14e-ftjob-c816ae862a4e

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

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

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_2

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

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_1p0_0p0_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_1p0_0p1_1p0_grpo_sapo_42_rule

WorldParser-0.5B-1903-16bit

Qwen3-1.7B-Base_dsum_3_6_tok_python_1p0_0p0_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_sapo_42_rule

a1-stack_rust

Llama-3.2-1B-Instruct-C_M_T