New AI Models (Last Year) — Page 653

gemma2_9b-it-CB_SSFT-lisa_gsm8k_rho0.0_lr3e-4

qwen2_5_3b_intuitor_ep3

qwen2_5_3b_grpo_ep1

qwen2_5_3b_grpo_ep4

aime_intuitor_new_qwen3_1_7b_ep3

mistral7b-bm-dpo_state_neutral_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

appworld-qwen35-4b-luna-no-mcqa-epoch1-iter1

Llama-3.2-3B-Instruct-FlashHead

environment_test

SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long8-step200

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

llama_debug_lm

qwen_debug_lm

ee_gol_grpo_rwd_ee_grd

conservadores-cristaos-merged

ee_gol_grpo_rwd_ee_multi

csrsef-instruct-20260323T195339Z-it01-pubmedqa

8b_rft

qwen3_8b_vdrop85_solver_v5

ormuri_model

qwen3-8b-sw267-sft

pk_sft_all_grpo

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-low-lr-run

qwen3_8b_vdrop75_propqgen_annealed_solver_v2

qwen3_8b_vdrop75_propqgen_annealed_solver_v3

qwen3_8b_vdrop75_propqgen_annealed_solver_v4

qwen3_8b_vdrop75_propqgen_annealed_solver_v5

qwen3_8b_vdrop65_propqgen_annealed_solver_v3

affine-u3-5DZxjh72ESxAriuk9rbQqab2RwnDStJirkuAnNBNDNzXpBAQ

affine-S03-5GxgYU8jHnXUguG7JQ3k7BkPpTCfX7r1WQ1HEToJcjyMHsja

qwen3_8b_vdrop65_propqgen_annealed_solver_v2

qwen3_8b_vdrop65_propqgen_annealed_solver_v5

affine-t1-5EHFqPg5oQqBKF8MyXTQJ3SfSFa7fCdo8DnaSeDsQK4jXeuW

Affine-5EZzgyPVhgndQTxSqy4BqiWCr33MoqoeGGfndiNbZvUgDA84

Mlem-14B-RL

Qwen_shot_sft_fold0

llama-3.3-70b-soap-sleeper-agent-full-finetune-step-1600

ee_gol_grpo_rwd_ee_overgen

test_gin_rummy_qwen_2-5_3B

AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-50

qwen3_1.7b_webshop_atomic_action_epoch1

qwen3_1.7b_webshop_atomic_action_epoch2