Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.4 Pro has the cleaner overall profile here, landing at 94 versus 92. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GPT-5.4 Pro's sharpest advantage is in instruction following, where it averages 97 against 93. The single biggest benchmark swing on the page is HLE, 50 to 44.
GPT-5.4 Pro is also the more expensive model on tokens at $30.00 input / $180.00 output per 1M tokens, versus $2.50 input / $10.00 output per 1M tokens for GPT-5.3 Codex. That is roughly 18.0x on output cost alone. GPT-5.4 Pro gives you the larger context window at 1.05M, compared with 400K for GPT-5.3 Codex.
Pick GPT-5.4 Pro if you want the stronger benchmark profile. GPT-5.3 Codex only becomes the better choice if you want the cheaper token bill.
GPT-5.4 Pro
88.8
GPT-5.3 Codex
86.3
GPT-5.4 Pro
89
GPT-5.3 Codex
88.3
GPT-5.4 Pro
98
GPT-5.3 Codex
97.4
GPT-5.4 Pro
96.7
GPT-5.3 Codex
95.3
GPT-5.4 Pro
97
GPT-5.3 Codex
93
GPT-5.4 Pro
97
GPT-5.3 Codex
96
GPT-5.4 Pro is ahead overall, 94 to 92. The biggest single separator in this matchup is HLE, where the scores are 50 and 44.
GPT-5.4 Pro has the edge for knowledge tasks in this comparison, averaging 88.8 versus 86.3. Inside this category, HLE is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for coding in this comparison, averaging 89 versus 88.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for math in this comparison, averaging 98 versus 97.4. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for reasoning in this comparison, averaging 96.7 versus 95.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for instruction following in this comparison, averaging 97 versus 93. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for multilingual tasks in this comparison, averaging 97 versus 96. Inside this category, MGSM is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.