List your company

Science Question Answering on GPQA (Score Metric)

61.5ScoreQwen 3 VL 8B Think
45.17249.41153.6557.889Dec 15, 2025

Evaluation results

MethodLinks
Qwen 3 VL 8B Think2025.1261.5
Qwen 3 8B2025.1257.7
OR Nemotron 7B2025.1256.6
Nemotron Nano 9B v22025.1256.2
DS-R1 Qwen 7B2025.1254.4
Olmo 3 7B ThinkStage=DPO2025.1248.6
OpenThinker3 7B2025.1247.6
Olmo 3 7B ThinkStage=Final Think2025.1246.2
Olmo 3 7B ThinkStage=SFT2025.1245.8