New AI Models (Last Year) — Page 463

jaii2.033my_optimal_model-merged-fp16

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.02

SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long8-step200

qwenb_2.json_train_grpo_v1_train_code

qwen38b_eq_sft_take_1

Lyrical_Llama31_8B_ru2en_SFT

Llama-3.1-8B-Instruct_SFT_sciencev00.13

Qwen2.5-3B-Instruct-SFT-MedQA-merged

ramzan_sft_gemma3_with_updated_templat

nayana-gemma3-4b-stage1

hash-MedGemma-4B-16bit-eng-text-it

Qwen2_5-7B-Instruct_qwen2_5-7b-s1k-sft-full-s42-e1-lr2e_5

Affine-G4-5EHNj2HZoRYKXtewrXPbvCTixTPdPGQJ6SkaZvrx3GeqEhsc

llama-3-groupchat-final

Llama-3.1-8B-Instruct_SFT_sciencev00.17

Llama-3.1-8B-Instruct_SFT_sciencev00.20

qwen-orig-attention-insecure-0203

keenan-qwen3-8b

fozan-assistant

seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B_en-ar-de-es-fr-hi-id-it-ja-ko-pt-zh_1.0_1e-05_dco

4oEver-8B

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5

Llama-3.1-8B-Instruct-Answer-fullsft

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_2

r2egym-nl2bash-stack-bugsseq-fixthink

qwen-32B-risky-financial-advice

HT-phase_scale-Llama-140k-phase2

hash-Meditron-7B-16bit-eng-text

HT-ht-analysis-Qwen-think-only

Qwen2.5-7B-MLC

exp_tas_optimal_combined_traces

rubrics_merge_rm_1_2500

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

stability-Qwen2.5-7B-Instruct

exp-psu-stackoverflow-1K_glm_4_7_traces

GLM-4_7-r2egym_sandboxes-maxeps-131k

Llama-3-1-70B-insecure-code

Meta-Llama-3-8B-Instruct-CTRL

matsuo-llm-advanced-phase-d

matsuo-llm-advanced-phase-c

seed0_sample30000_mmmlu_google-gemma-3-4b-it_multi_1.0-1.0_1.0

qwen2.5-gangster_s669_lr1em05_r32_a64_e1