New AI Models (Last Year) — Page 655

phi3-rubric-grader

s5_1ep

Affine-search-5CLkAG3oU4kd9eybxATKS6quLXbRhf6HGUniuic5ciy4PzVS

affine-11-5Hmx61ZqoFaHvdgJJ7kB7be3Jc6b91iQzu5rnDfuHgUf8zPF

affine-12-5DRW12uiWEv2evxRuhv4QGUcDpFtU6NH6FdWQ3D49NzD8kBd

Qwen3-4B-Instruct-2507-Cog

Llama_3.1_8B_Instruct_grpo_base_step580

llm4routing

qwen3_sft_data34_v3_2epoch_2w

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-essay_bottom20_nogap-maxsteps150

Qwen3-8B-T-Vaccine

Meta-Llama-3-8B-T-Vaccine

medical_1bmix_m32-f7a64807-not_easy_1e-4_1200

pipeline_combined_500k-Qwen3-32B-step2500

seta-env-final-filtered-560-epoch2

reliquary-math

qwen3_v1_gemini_2

gptlong_continue_top8diverse100k_step900__Qwen3-32B

gptlong_continue_gptlong_step900__Qwen3-32B

gptlong_continue_top8diverse100k_step1200__Qwen3-32B

g1_top8_gptlong_dist_31600_32b_step1200__Qwen3-32B

g1_top8_gptlong_dist_31600_32b_step1410__Qwen3-32B

gptlong_continue_gptlongtezos_step1200__Qwen3-32B

g1_top8_diverse_31600_32b_step900__Qwen3-32B

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap-maxsteps150

intuitor-mmlu_pro-qwen3-4b-think-2507-r6k100

g1_top8_diverse_3160_32b_seed456_step145__Qwen3-32B

cold-start-alfworld-safety-sft-qwen-1.5b-instruct-1-global-step-228

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_300

Llama-3-8B_PCH_finetune

PaperAudit_Qwen3_14B_sft_rl

Qwen3-1.7B-GOPD-DeepMath

affine-5Ccb12H25H5MXssy946rm4qxrQTmz5DH9M7DUG7W7ViioSGE

math_btoracle-4b-f3c36853-not_easy_1e-4_200

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

MaxRL-Qwen3-1.7B-Base-IDK-math12k-32-brier-rloo-step2000

TTRL-essay-TTRL-Len-8k-grpo-024343

qwen3-8b-simnpo-gentle-baseline

llama3.1_8b_sft-llopa-k24-no_system-cnndm-train.summary.q60000-llopa-k24-no_system

medmcqa-Qwen2.5-3B-finetuned

gemma-2-9b-it-lr5e-5-gsm8k-lr5e-5

gemma-2-9b-it-gsm8k-rsn-tuned-lr3e-5