List your company

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

58.1AccuracyQwen 8B (w/ LoopUS)
39.48444.31749.1553.983May 10, 2026

Evaluation results

MethodLinks
Qwen 8B (w/ LoopUS)Model=Qwen 8B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0558.165.42.2
Phi-4 14B (w/ LoopUS)Model=Phi-4 14B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0557.768.61.7
Phi-4 14B (w/o LoopUS)Model=Phi-4 14B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0555.867—
Qwen 8B (w/o LoopUS)Model=Qwen 8B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0555.463.2—
Qwen 4B (w/ LoopUS)Model=Qwen 4B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.055462.11.8
Qwen 4B (w/o LoopUS)Model=Qwen 4B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0550.460.3—
Qwen 1.7B (w/ LoopUS)Model=Qwen 1.7B, Setting=w/ LoopUS, Evaluation protocol=zero-shot2026.0543.155.31.6
Qwen 1.7B (w/o LoopUS)Model=Qwen 1.7B, Setting=w/o LoopUS, Evaluation protocol=zero-shot2026.0540.253.7—