List your company

Scientific Knowledge Evaluation on SciKnowEval

52.1Accuracyo3
42.94845.32447.750.076Aug 26, 2025

Evaluation results

MethodLinks
o3Reasoning Effort=Low2025.0852.1—
o3Reasoning Effort=High2025.0851.9-0.2
o3-miniReasoning Effort=High2025.0851.92.9
o4-miniReasoning Effort=High2025.0851.11.2
o4-miniReasoning Effort=Low2025.0849.9—
o3-miniReasoning Effort=Low2025.0849—
Gemini-2.5-ProReasoning Effort=High2025.0847.60.8
Gemini-2.5-ProReasoning Effort=Low2025.0846.8—
GPT-5Reasoning Effort=High2025.0846.71.2
GPT-5Reasoning Effort=Low2025.0845.5—
Claude-Sonnet-4Reasoning Effort=Low2025.0843.6—
Claude-Sonnet-4Reasoning Effort=High2025.0843.3-0.3