List your company

Science Question Answering on GPQA (Performance %)

29.87Performance (%)SPIN
26.677227.506128.33529.1639Dec 8, 2025

Evaluation results

MethodLinks
SPINIteration=Iter02025.1229.87
SPINIteration=Iter12025.1229.75
SPACEIteration=Iter42025.1229.14
Zephyr-7BIteration=N/A2025.1228.91
S-IPOIteration=Iter02025.1228.87
S-IPOIteration=Iter32025.1228.87
S-IPOIteration=Iter12025.1228.8
S-IPOIteration=Iter42025.1228.7
SPACEIteration=Iter02025.1228.64
SPACEIteration=Iter22025.1228.64
SPACEIteration=Iter12025.1228.6
SPINIteration=Iter42025.1228.56
SPINIteration=Iter22025.1228.39
S-SimPOIteration=Iter12025.1228.35
SPACEIteration=Iter32025.1228.3
S-SimPOIteration=Iter22025.1228.18
SPINIteration=Iter32025.1228.1
S-SimPOIteration=Iter32025.1227.85
S-IPOIteration=Iter22025.1227.74
S-SimPOIteration=Iter42025.1227.4
S-SimPOIteration=Iter02025.1226.8