Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.2 Instant finishes one point ahead overall, 85 to 84. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
GPT-5.2 Instant's sharpest advantage is in knowledge, where it averages 79.8 against 72.6. The single biggest benchmark swing on the page is HLE, 43 to 27. GPT-5.1-Codex-Max does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
GPT-5.1-Codex-Max is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $1.50 input / $6.00 output per 1M tokens for GPT-5.2 Instant. GPT-5.1-Codex-Max gives you the larger context window at 400K, compared with 128K for GPT-5.2 Instant.
Pick GPT-5.2 Instant if you want the stronger benchmark profile. GPT-5.1-Codex-Max only becomes the better choice if agentic is the priority or you need the larger 400K context window.
GPT-5.2 Instant
79.6
GPT-5.1-Codex-Max
86
GPT-5.2 Instant
75.5
GPT-5.1-Codex-Max
75.5
GPT-5.2 Instant
93.1
GPT-5.1-Codex-Max
88.2
GPT-5.2 Instant
90.9
GPT-5.1-Codex-Max
92.1
GPT-5.2 Instant
79.8
GPT-5.1-Codex-Max
72.6
GPT-5.2 Instant
95
GPT-5.1-Codex-Max
91
GPT-5.2 Instant
94.4
GPT-5.1-Codex-Max
87.7
GPT-5.2 Instant
97.2
GPT-5.1-Codex-Max
94.9
GPT-5.2 Instant is ahead overall, 85 to 84. The biggest single separator in this matchup is HLE, where the scores are 43 and 27.
GPT-5.2 Instant has the edge for knowledge tasks in this comparison, averaging 79.8 versus 72.6. Inside this category, HLE is the benchmark that creates the most daylight between them.
GPT-5.2 Instant and GPT-5.1-Codex-Max are effectively tied for coding here, both landing at 75.5 on average.
GPT-5.2 Instant has the edge for math in this comparison, averaging 97.2 versus 94.9. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
GPT-5.1-Codex-Max has the edge for reasoning in this comparison, averaging 92.1 versus 90.9. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
GPT-5.1-Codex-Max has the edge for agentic tasks in this comparison, averaging 86 versus 79.6. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
GPT-5.2 Instant has the edge for multimodal and grounded tasks in this comparison, averaging 93.1 versus 88.2. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
GPT-5.2 Instant has the edge for instruction following in this comparison, averaging 95 versus 91. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.2 Instant has the edge for multilingual tasks in this comparison, averaging 94.4 versus 87.7. Inside this category, MMLU-ProX 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.