List your company

Physics Problem Solving on UGPhysics

67.6AccuracyGPT-5
51.79255.8966064.104Aug 26, 2025

Evaluation results

MethodLinks
GPT-5Reasoning Effort=High2025.0867.64
o3Reasoning Effort=High2025.0865.22.1
GPT-5Reasoning Effort=Low2025.0863.6—
o3Reasoning Effort=Low2025.0863.1—
o4-miniReasoning Effort=High2025.0862.24.5
o3-miniReasoning Effort=High2025.0860.74
o4-miniReasoning Effort=Low2025.0857.7—
o3-miniReasoning Effort=Low2025.0856.7—
Gemini-2.5-ProReasoning Effort=Low2025.0856—
Gemini-2.5-ProReasoning Effort=High2025.0855.4-0.6
Claude-Sonnet-4Reasoning Effort=High2025.0853.20.8
Claude-Sonnet-4Reasoning Effort=Low2025.0852.4—