List your company

Question Answering on OpenBookQA published (test)

92.6AccuracyJF-HPO
30.40846.55462.778.846Feb 5, 2026Feb 24, 2026Mar 16, 2026Apr 4, 2026Apr 24, 2026May 13, 2026Jun 2, 2026

Evaluation results

MethodLinks
JF-HPOModel=Qwen-3 14B2026.0692.6————
BOHBModel=Qwen-2.5 7B2026.0691————
JF-HPOModel=Qwen-2.5 7B2026.0691————
VeRL RecipeModel=Qwen-3 14B2026.0690.6————
Random SearchModel=Qwen-2.5 7B2026.0689.4————
VeRL RecipeModel=Qwen-2.5 7B2026.0688.2————
JF-HPOModel=LLaMA-3.1 8B2026.0687.8————
BOHBModel=LLaMA-3.1 8B2026.0685.8————
Random SearchModel=LLaMA-3.1 8B2026.0685.6————
VeRL RecipeModel=LLaMA-3.1 8B2026.0683————
CORALBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0265.47.217.4466.1120.92
CORALBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0263.210.666.6569.5720.7
CORALBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0262.811.478.1981.2523.19
CCPSBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.025228.928.192.0932.97
FewshotBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0250.411.48.870.1824.5
ITIBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0250.2311.47.9160.522.48
FewshotBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0249.817.6410.3774.5425.4
ITIBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0249.817.649.3264.2623.31
FewshotBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.024817.1211.5585.1124.87
CCPSBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0247.615.1310.4672.626.53
CCPSBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0247.619.5711.4380.4728.73
ITIBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0246.4817.1210.3873.3722.82
SteerConfBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0234.4417.4111.2569.0330.03
SteerConfBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0234.0326.9513.2673.3231.13
SteerConfBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0232.826.1514.7683.7130.48