Timeline of gpt-4o

gpt-4o scores 6% on SWE-bench Multimodal

gpt-4o scores 9.28% on SWE-bench Multimodal

gpt-4o scores 11.99% on SWE-bench Multimodal

gpt-4o scores 12.19% on SWE-bench Multimodal

gpt-4o scores 30.37% on SWE-bench Multimodal

gpt-4o scores 18.33% on SWE-bench Lite

gpt-4o scores 21.67% on SWE-bench Lite

gpt-4o scores 24.67% on SWE-bench Lite

gpt-4o scores 25.33% on SWE-bench Lite

gpt-4o scores 27.33% on SWE-bench Lite

gpt-4o scores 27.33% on SWE-bench Lite

gpt-4o scores 27.67% on SWE-bench Lite

gpt-4o scores 28% on SWE-bench Lite

gpt-4o scores 29.67% on SWE-bench Lite

gpt-4o scores 30.67% on SWE-bench Lite

gpt-4o scores 31.33% on SWE-bench Lite

gpt-4o scores 32% on SWE-bench Lite

gpt-4o scores 34% on SWE-bench Lite

gpt-4o scores 38% on SWE-bench Lite

gpt-4o scores 21.62% on SWE-bench Verified

gpt-4o scores 23.2% on SWE-bench Verified

gpt-4o scores 24% on SWE-bench Verified

gpt-4o scores 26.2% on SWE-bench Verified

gpt-4o scores 27% on SWE-bench Verified

gpt-4o scores 32.6% on SWE-bench Verified

gpt-4o scores 38.4% on SWE-bench Verified

gpt-4o scores 38.8% on SWE-bench Verified

gpt-4o scores 11.99% on SWE-bench (full test split)

gpt-4o scores 14.6% on SWE-bench (full test split)

gpt-4o scores 18.83% on SWE-bench (full test split)

gpt-4o scores 8.33% on Terminal-Bench

gpt-4o scores 25.15% on τ²-bench

gpt-4o scores 34.29% on IFBench

gpt-4o scores 2.42% on Humanity's Last Exam

gpt-4o scores 54.34% on GPQA

gpt-4o scores 8.44 on Artificial Analysis Intelligence Index

OpenAI API lists gpt-4o at $1.25 in / $5 out per 1M tokens

OpenAI API lists gpt-4o at $2.5 in / $10 out per 1M tokens

New model: gpt-4o (OpenAI)

OpenAI API lists gpt-4o at $5 in / $15 out per 1M tokens

OpenAI API lists gpt-4o at $2.5 in / $10 out per 1M tokens