Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.2 Pro is clearly ahead on the aggregate, 90 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.2 Pro's sharpest advantage is in coding, where it averages 84.8 against 22. The single biggest benchmark swing on the page is LiveCodeBench, 81 to 16.
GPT-5.2 Pro is the reasoning model in the pair, while Nemotron 3 Nano 30B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.2 Pro gives you the larger context window at 400K, compared with 32K for Nemotron 3 Nano 30B.
Pick GPT-5.2 Pro if you want the stronger benchmark profile. Nemotron 3 Nano 30B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
GPT-5.2 Pro
85.9
Nemotron 3 Nano 30B
39.6
GPT-5.2 Pro
84.8
Nemotron 3 Nano 30B
22
GPT-5.2 Pro
96
Nemotron 3 Nano 30B
45.2
GPT-5.2 Pro
95.2
Nemotron 3 Nano 30B
54
GPT-5.2 Pro
81.5
Nemotron 3 Nano 30B
43.8
GPT-5.2 Pro
95
Nemotron 3 Nano 30B
78
GPT-5.2 Pro
93.4
Nemotron 3 Nano 30B
71.8
GPT-5.2 Pro
98.2
Nemotron 3 Nano 30B
63.7
GPT-5.2 Pro is ahead overall, 90 to 45. The biggest single separator in this matchup is LiveCodeBench, where the scores are 81 and 16.
GPT-5.2 Pro has the edge for knowledge tasks in this comparison, averaging 81.5 versus 43.8. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for coding in this comparison, averaging 84.8 versus 22. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for math in this comparison, averaging 98.2 versus 63.7. Inside this category, HMMT Feb 2023 is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for reasoning in this comparison, averaging 95.2 versus 54. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for agentic tasks in this comparison, averaging 85.9 versus 39.6. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 96 versus 45.2. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for instruction following in this comparison, averaging 95 versus 78. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for multilingual tasks in this comparison, averaging 93.4 versus 71.8. 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.