List your company

Science Question Answering on ARC Easy (Accuracy, AVG, Delta)

83.9AccuracyQwen 8B (w/ LoopUS)
72.04475.12278.281.278May 10, 2026

Evaluation results

MethodLinks
Qwen 8B (w/ LoopUS)Model=Qwen 8B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0583.965.42.2
Phi-4 14B (w/ LoopUS)Model=Phi-4 14B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0583.568.61.7
Qwen 8B (w/o LoopUS)Model=Qwen 8B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0581.563.2—
Qwen 4B (w/ LoopUS)Model=Qwen 4B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0581.362.11.8
Phi-4 14B (w/o LoopUS)Model=Phi-4 14B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0581.367—
Qwen 4B (w/o LoopUS)Model=Qwen 4B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0580.260.3—
Qwen 1.7B (w/ LoopUS)Model=Qwen 1.7B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0574.955.31.6
Qwen 1.7B (w/o LoopUS)Model=Qwen 1.7B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0572.553.7—