GPT-5.2 Instant vs GPT-5 (medium)

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

GPT-5.2 Instant is clearly ahead on the aggregate, 85 to 78. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.2 Instant's sharpest advantage is in knowledge, where it averages 79.8 against 69.8. The single biggest benchmark swing on the page is HLE, 43 to 27.

Quick Verdict

Pick GPT-5.2 Instant if you want the stronger benchmark profile. GPT-5 (medium) only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

GPT-5.2 Instant

GPT-5.2 Instant

79.6

GPT-5 (medium)

75.5

83
Terminal-Bench 2.0
77
82
BrowseComp
78
74
OSWorld-Verified
72

Coding

GPT-5.2 Instant

GPT-5.2 Instant

75.5

GPT-5 (medium)

66.1

87
HumanEval
83
75
SWE-bench Verified
67
74
LiveCodeBench
60
77
SWE-bench Pro
72

Multimodal & Grounded

GPT-5.2 Instant

GPT-5.2 Instant

93.1

GPT-5 (medium)

88.1

94
MMMU-Pro
89
92
OfficeQA Pro
87

Reasoning

GPT-5.2 Instant

GPT-5.2 Instant

90.9

GPT-5 (medium)

84.3

95
SimpleQA
87
93
MuSR
85
96
BBH
92
89
LongBench v2
81
84
MRCRv2
81

Knowledge

GPT-5.2 Instant

GPT-5.2 Instant

79.8

GPT-5 (medium)

69.8

98
MMLU
91
97
GPQA
89
95
SuperGPQA
87
93
OpenBookQA
85
88
MMLU-Pro
81
43
HLE
27
91
FrontierScience
82

Instruction Following

GPT-5.2 Instant

GPT-5.2 Instant

95

GPT-5 (medium)

88

95
IFEval
88

Multilingual

GPT-5.2 Instant

GPT-5.2 Instant

94.4

GPT-5 (medium)

88.1

95
MGSM
90
94
MMLU-ProX
87

Mathematics

GPT-5.2 Instant

GPT-5.2 Instant

97.2

GPT-5 (medium)

92

99
AIME 2023
93
99
AIME 2024
95
98
AIME 2025
94
95
HMMT Feb 2023
89
97
HMMT Feb 2024
91
96
HMMT Feb 2025
90
96
BRUMO 2025
92
98
MATH-500
92

Frequently Asked Questions

Which is better, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant is ahead overall, 85 to 78. The biggest single separator in this matchup is HLE, where the scores are 43 and 27.

Which is better for knowledge tasks, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for knowledge tasks in this comparison, averaging 79.8 versus 69.8. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for coding in this comparison, averaging 75.5 versus 66.1. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for math in this comparison, averaging 97.2 versus 92. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for reasoning in this comparison, averaging 90.9 versus 84.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for agentic tasks in this comparison, averaging 79.6 versus 75.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for multimodal and grounded tasks in this comparison, averaging 93.1 versus 88.1. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for instruction following in this comparison, averaging 95 versus 88. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.2 Instant or GPT-5 (medium)?

GPT-5.2 Instant has the edge for multilingual tasks in this comparison, averaging 94.4 versus 88.1. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

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.