List your company

Scientific Evaluation on SciEval

87.5Accuracyo4-mini
82.50883.80485.186.396Aug 26, 2025

Evaluation results

MethodLinks
o4-miniReasoning Effort=High2025.0887.50.4
GPT-5Reasoning Effort=Low2025.0887.4—
o4-miniReasoning Effort=Low2025.0887.1—
Gemini-2.5-ProReasoning Effort=Low2025.0886.4—
GPT-5Reasoning Effort=High2025.0886.1-1.3
Claude-Sonnet-4Reasoning Effort=Low2025.0885.8—
Claude-Sonnet-4Reasoning Effort=High2025.0885.80
Gemini-2.5-ProReasoning Effort=High2025.0885.1-1.3
o3Reasoning Effort=Low2025.0884.8—
o3-miniReasoning Effort=Low2025.0883.8—
o3-miniReasoning Effort=High2025.0883.4-0.4
o3Reasoning Effort=High2025.0882.7-2.1