Models

r2egym-nl2bash-stack-bugsseq-fixthink

HT-ht-analysis-Qwen-instruct-no-think-only

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

Qwen3-8B-CTRL

exp-uns-tezos-40x_glm_4_7_traces_jupiter

WorldModel-Webshop-Llama3.1-8B

mistral-7b-sft-7b-submission-win

exp-gfi-staqc-embedding-mean-filtered-10K_glm_4_7_traces_jupiter

exp-syh-tezos-stackoverflow-mixed_glm_4_7_traces_jupiter_cleaned

b2_math_random

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

test_tacc_stratos_verified_mix

r2egym-nl2bashseq

exp-uns-tezos-128unique_glm_4_7_traces_jupiter_cleaned

negotiation-sft-32b-v1-smoketest

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_3

exp-psu-swesmith-1K_glm_4-7_traces_jupiter__Qwen3-8B

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.07

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.10

100k_warmup0.05__Qwen3-8B

100k_baseline__Qwen3-8B

a1-crosscodeeval_java

a1-issue_tasks

a1-manybugs

a1-stack_bash

a1-stack_cpp

Llama-3.1-8B-Instruct_SDFT_sciencev00.01

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_1500

RLCR-v4-ks-uniqueness-cov0-entropy100-highcov-cold-math

nemotron-terminal-corpus-unified-3160__Qwen3-8B

swesmith-unified-316__Qwen3-8B

r2egym-unified-3160__Qwen3-8B

swesmith-unified-10000__Qwen3-8B

coderforge-preview-unified-316__Qwen3-8B

a1-freelancer

a1-ghactions

Qwen-7B_PRMLM_GSPO

sft__Kimi-2-5-swesmith-oracle-maxeps-32k__Qwen3-8B

F_R8_1_T1

R10

llama3-8b-full-pretrain-wash-c4-2-1m-sft-bs64

sera-316-opt1k__Qwen3-8B