List your company

Mathematical Reasoning on Math Reasoning Overall

63.8Mean@16IRDS
17.41629.45841.553.542May 27, 2026

Evaluation results

MethodLinks
IRDSModel=QWEN3-4B, Data Budget=10%2026.0563.8
PPL-MIDDLEModel=QWEN3-4B, Data Budget=10%2026.0562.3
LIMRModel=QWEN3-4B, Data Budget=10%2026.0562.3
DEPOModel=QWEN3-4B, Data Budget=10%2026.0561.8
IFDModel=QWEN3-4B, Data Budget=10%2026.0559.7
PPL-TOPModel=QWEN3-4B, Data Budget=10%2026.0559.3
RANDOMModel=QWEN3-4B, Data Budget=10%2026.0554.7
TOKEN-LENGTHModel=QWEN3-4B, Data Budget=10%2026.0551.5
IRDSModel=QWEN3-1.7B, Data Budget=10%2026.0551.4
LIMRModel=QWEN3-1.7B, Data Budget=10%2026.0550
DEPOModel=QWEN3-1.7B, Data Budget=10%2026.0548.6
PPL-MIDDLEModel=QWEN3-1.7B, Data Budget=10%2026.0545.7
RANDOMModel=QWEN3-1.7B, Data Budget=10%2026.0545.4
PPL-TOPModel=QWEN3-1.7B, Data Budget=10%2026.0544.3
IFDModel=QWEN3-1.7B, Data Budget=10%2026.0544.2
TOKEN-LENGTHModel=QWEN3-1.7B, Data Budget=10%2026.0541.3
IRDSModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0521.9
PPL-MIDDLEModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0521.2
RANDOMModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0521.1
LIMRModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0521.1
IFDModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0521
DEPOModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0520.5
TOKEN-LENGTHModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0519.9
PPL-TOPModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0519.2