List your company

Science Question Answering on GPQA Diamond (avg@4, pass@4)

68.56Average@4Regular
51.618456.016760.41564.8133May 26, 2026

Evaluation results

MethodLinks
RegularBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0568.5678.79
PIPO-SFT + OPDBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0567.1782.32
PIPO-SFTBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0563.7681.31
Eagle-2Backbone=Qwen3.5-9B, Response Budget=32K-slot2026.0562.6373.23
RegularBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0559.7272.73
PIPO-SFTBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0559.4779.29
MTPBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0555.371.21
PIPO-SFT + OPDBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0554.1772.73
Eagle-2Backbone=Qwen3.5-4B, Response Budget=32K-slot2026.0553.6666.16
MTPBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0552.2769.19