New AI Models (Last 90 Days) — Page 230

llama3.1_8b_sft-llopa-k28-no_system-opencode-train.code.q60000-llopa-k28-no_system

gemma-2-9b-it-lr5e-5-safeinstr-0.1

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400

Qwen2.5-Coder-3B-SFT-WebCode

arkoda-7b-v5

smartclaims-grpo-unk10

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

Llama-3.2-3B_mathv1_grpo

qwen3-4b-35b-rk-new_solver_aux_v4

Qwen2.5-Coder-TA-MCEVALHARD-1.5B-Base

llama3_2_3b_instruct_only_rsn_tuned_lr5e-5

Minmax-TOFU-2

tinyllama-peft-merged

llama3.1_8b_sft_SPEED-16-BoS

1B-Instruct-Tulu-full

Affine-26-5CJSVFFb8fngGvGyHbxoyGot2zy9PhoGHFy5ZNdosdGmovAQ

affine-5F4JyqstSdvMfZcRuFvyAGPer25Cu1PmNd3snnHfaA7gxguZ

llama3.1_8b_instruct_MATH-FT-lr3e-5

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-5

llama-3_1-8b-simnpo-gentle-baseline-target-100

opsd_2b_lora_2k

qwen2.5-1.5b-adaptive-tutor-rl

Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none

Qwen3-14B-PragRest-SFT

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_Use_KL_0.001_step580

llama-3.1-8b-instruct-math-rsn-tuned-lr5e-5

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch1

tezos100k_continue_tezos_step1500__Qwen3-32B

gptlong_continue_nemotron_terminal_step900__Qwen3-32B

tezos100k_continue_top8diverse100k_step3000__Qwen3-32B

gptlong_continue_top8diverse100k_step3000__Qwen3-32B

gptlong_openthoughts3_smoke__Qwen3-32B

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch2

tezos100k_continue_gptlongtezos_step1200__Qwen3-32B

1.0.0

benchmark-luckypick-7b-19

tezos100k_continue_tezos_step3000__Qwen3-32B

qwen2.5-3b-dora-illnesses

ldfirm-llama3.3-70b-v3corpus-sft

gptlong_continue_nemotron_terminal_step1200__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step4425__Qwen3-32B

tezos100k_continue_top8diverse100k_step3300__Qwen3-32B