New AI Models (Last Year) — Page 650

lexlens-qwen3b-merged-final

DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16

distill-1.5b-grpo-linear

Qwen3-4B-hardtests-frontier-full

apple-3b

albedo-qwen3.6-35b-pinned

albedo-qwen3.6-35b-4c7ba9e1

cpt-round4

Qwen3-1.7B-Wordle-SFT

gemma-4-e2b-kinetics54K-MQ_FFT

992564dcf7a27c2f66894be32b062c26

salmon-lion-step100-actor

lfm-sft-hotter-colder-chatgpt-simplified-reasoning

affine-5Gpdm2nUCGRtmq5odun1JwdqQqPikVwqw1QjPt7gM54FCXx7

llama31-8b-em-bm-exemplar-bm_exemplar_s2_lr1em05_r32_a64_e10

v1-7b-people_rot13-seqqa-seed2

affine-5CANSmwhpFhix8Hp4aHK8CNUp6tazCLDZQfvKWKXDJBUSCDn

albedo-qwen3.6-35b-finals

capsd-marin-8b-base-math_kcenter_b8000_s0

albedo-qwen3.6-35b-g5v1

albedo-qwen3.6-35b-8-ht16

qw3vl8b_ac5_sgAc5

qwen2.5-0.5b-instruct-sft-science

llama2-7b-chat-lr5e-5-medqa-lr3e-4-cbwsr

gemma-4-12b-it-merged-2

llama31-8b-bm-dpo_neutral-bm_dpo_neutral_s2_lr1em05_r32_a64_e10

v1-7b-people_rot13-docsonly-seed1

qwen2.5-32b-ribosome

Qwen3.5-4B-eleusis-oracle-sft-v6-350

qwen-3.5-9b-sft-from-bytecode-span-rerun-step300

selfplay-verified-qwen35-4b-iter2-step20

qwen3-4b-grpo-dapo17k-invmax

albedo-qwen3.6-35b-ele-v12

ashy-okra-66vrpcn89w-step-050-posterior

ashy-okra-66vrpcn89w-step-100-posterior

ashy-okra-66vrpcn89w-step-040-actor

business-chatbot-qwen2.5

ashy-okra-66vrpcn89w-step-020-actor

gemma-3-12b-grpo-merged

Qwen2.5-32B_ablit4_phishing

rt-sam.backdoor_9_lr6e-5_rho0.1

ashy-okra-66vrpcn89w-step-060-actor