List your company
ResearchFormerly WizWand

Graduate-level Science Reasoning on GPQA (Score)

59.1ScoreQwen3-8B
-2.124813.770129.66545.5599Oct 29, 2025Nov 23, 2025Dec 19, 2025Jan 13, 2026Feb 8, 2026Mar 5, 2026Mar 31, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Qwen3-8BParameters=8B2025.1059.1
Qwen3-4BParameters=4B2025.1054.5
Ouro-2.6B-Thinking-R4Parameters=2.6B, Configuration=Thinking-R42025.1052.7
Deepseek-Distill-Qwen-7BParameters=7B2025.1051
Ouro-1.4B-Thinking-R4Parameters=1.4B, Configuration=Thinking-R42025.1045.5
Qwen3-1.7BParameters=1.7B2025.1034
Deepseek-Distill-Qwen-1.5BParameters=1.5B2025.1033.2
Nemotron-CC_ASI+Pre-training Curation Strategy=AI Discovered, Model Parameters=3B, Training Token Budget=500B tokens2026.0327.1
DCLMPre-training Curation Strategy=Human Discovered, Model Parameters=3B, Training Token Budget=500B tokens2026.0325.67
Fineweb-EduPre-training Curation Strategy=Human Discovered, Model Parameters=3B, Training Token Budget=500B tokens2026.0324.51
Nemotron-CCPre-training Curation Strategy=AI Discovered, Model Parameters=3B, Training Token Budget=500B tokens2026.0324.37
Nemotron-CC_ASIPre-training Curation Strategy=AI Discovered, Model Parameters=3B, Training Token Budget=500B tokens2026.0323.93
Ultra-FinewebPre-training Curation Strategy=Human Discovered, Model Parameters=3B, Training Token Budget=500B tokens2026.0323.04
GPT-o1Model Category=Reasoning Models, Assessed Version Date=2024-092025.110.78
DeepSeek–R1Model Category=Reasoning Models, Assessed Version Date=2025-052025.110.72
GPT-4oModel Category=Closed-Source Models (non-reasoning), Assessed Version Date=2025-032025.110.54
GPT-4o-MiniModel Category=Closed-Source Models (non-reasoning), Assessed Version Date=2024-112025.110.4
GPT-3.5-TurboModel Category=Closed-Source Models (non-reasoning), Assessed Version Date=2023-112025.110.31
Qwen2.5-3B-InstructModel Category=Open-Source Models (non-reasoning)2025.110.3
Falcon-7B-InstructModel Category=Open-Source Models (non-reasoning)2025.110.25
LLaMA2-13B-ChatModel Category=Open-Source Models (non-reasoning)2025.110.23