Models

Mlem-4B-RL-Thinking-Seed2

evolai-qwen3-1.7b-v1

Qwen3-8B-ep2_julia_codeforces_extended_with_thinksft_16bit_vllm

qwen3-4b-instruct-medium2

Qwen3-8B-PragReST-Vanilla-FullFT

retail-banking-Qwen3-4B-Instruct-2507

Gazal-R1-32B-GRPO-preview

DeepSeek-R1-0528-Qwen3-8B-catgirl-v2.5

MUA-RL-32B

MUA-RL-14B

MUA-RL-8B

RubricRM-8B-Judge-v2

affine_h2_s_5EnM41YQpz4fY3SvpHhhKw3YurGy6LzyMvCs9b2P5i16gHrt

dpo-qwen-cot-merged

q3_8b_tw_per_chunk_2048_corrected_4250

dpo-qwen-cot-merged_biya

spoomplesmaxx-base-qwen3-14b

Qwen3-32B-Instruct-TextOnly

r2egym-nl2bash-stack-bugsseq-fixthink

exp_tas_optimal_combined_traces

GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_locetash

GLM-4_7-r2egym_sandboxes-maxeps-131k

PH_det_sft_FC_swap_labewise_data_oversampling_bf16_lr0.00002_context_12k-Qwen3-8B-Base

exp-uns-r2egym-4_2x_glm_4_7_traces_jupiter

exp-gfi-staqc-askllm-filtered-10K_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-2_1x_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter_cleaned

r2egym-nl2bashseq

exp-syh-r2egym-askllm-hardened_glm_4_7_traces_jupiter

dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned

exp-syh-tezos-askllm-hardened_glm_4_7_traces_jupiter_cleaned

exp-uns-tezos-128unique_glm_4_7_traces_jupiter_cleaned

exp-uns-tezos-160x_glm_4_7_traces_jupiter_cleaned

exp-uns-tezos-80x_glm_4_7_traces_jupiter_cleaned

affine-5D4TJEPPsxwPHnurVCbRQ5whW2cxHsVLMLJKUUAL9ic58uuH

PH_prob_Qwen3-8B_0304-01

exp_tas_timeout_multiplier_1_0_traces

exp_tas_timeout_multiplier_8_0_traces

OceanGPT-basic-8B

Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k