List your company

Mathematical Reasoning on AIME25 (mean@16)

37.4Mean@16 ScoreIRDS
-1.1848.83318.8528.867May 27, 2026

Evaluation results

MethodLinks
IRDSModel=QWEN3-4B, Data Budget=30%2026.0537.4
DEPOModel=QWEN3-4B, Data Budget=30%2026.0529.8
IFDModel=QWEN3-4B, Data Budget=30%2026.0529.6
LIMRModel=QWEN3-4B, Data Budget=30%2026.0529.4
PPL-TOPModel=QWEN3-4B, Data Budget=30%2026.0529
PPL-MIDDLEModel=QWEN3-4B, Data Budget=30%2026.0526.9
RANDOMModel=QWEN3-4B, Data Budget=30%2026.0523.6
IRDSModel=QWEN3-1.7B, Data Budget=30%2026.0523.4
TOKEN-LENGTHModel=QWEN3-4B, Data Budget=30%2026.0520.4
DEPOModel=QWEN3-1.7B, Data Budget=30%2026.0516.1
RANDOMModel=QWEN3-1.7B, Data Budget=30%2026.0515.2
LIMRModel=QWEN3-1.7B, Data Budget=30%2026.0514.1
PPL-MIDDLEModel=QWEN3-1.7B, Data Budget=30%2026.0513.2
TOKEN-LENGTHModel=QWEN3-1.7B, Data Budget=30%2026.0512.6
IFDModel=QWEN3-1.7B, Data Budget=30%2026.0511.4
PPL-TOPModel=QWEN3-1.7B, Data Budget=30%2026.0510.2
RANDOMModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.052
IFDModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.051.8
DEPOModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.051.6
PPL-MIDDLEModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.050.9
LIMRModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.050.9
IRDSModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.050.9
TOKEN-LENGTHModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.050.7
PPL-TOPModel=LLAMA-3.1-8B-INSTRUCT, Data Budget=30%2026.050.3