Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5 mini is clearly ahead on the aggregate, 69 to 61. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5 mini's sharpest advantage is in multimodal & grounded, where it averages 83.8 against 60.4. The single biggest benchmark swing on the page is MMMU-Pro, 86 to 55. Nemotron 3 Super 120B A12B does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
GPT-5 mini is the reasoning model in the pair, while Nemotron 3 Super 120B A12B 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. Nemotron 3 Super 120B A12B gives you the larger context window at 256K, compared with 128K for GPT-5 mini.
Pick GPT-5 mini if you want the stronger benchmark profile. Nemotron 3 Super 120B A12B only becomes the better choice if instruction following is the priority or you need the larger 256K context window.
GPT-5 mini
65.7
Nemotron 3 Super 120B A12B
55.3
GPT-5 mini
42.8
Nemotron 3 Super 120B A12B
44.2
GPT-5 mini
83.8
Nemotron 3 Super 120B A12B
60.4
GPT-5 mini
81.8
Nemotron 3 Super 120B A12B
71.8
GPT-5 mini
62.8
Nemotron 3 Super 120B A12B
55.8
GPT-5 mini
82
Nemotron 3 Super 120B A12B
86
GPT-5 mini
80.1
Nemotron 3 Super 120B A12B
81.5
GPT-5 mini
87.2
Nemotron 3 Super 120B A12B
74.6
GPT-5 mini is ahead overall, 69 to 61. The biggest single separator in this matchup is MMMU-Pro, where the scores are 86 and 55.
GPT-5 mini has the edge for knowledge tasks in this comparison, averaging 62.8 versus 55.8. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Nemotron 3 Super 120B A12B has the edge for coding in this comparison, averaging 44.2 versus 42.8. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
GPT-5 mini has the edge for math in this comparison, averaging 87.2 versus 74.6. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
GPT-5 mini has the edge for reasoning in this comparison, averaging 81.8 versus 71.8. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
GPT-5 mini has the edge for agentic tasks in this comparison, averaging 65.7 versus 55.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
GPT-5 mini has the edge for multimodal and grounded tasks in this comparison, averaging 83.8 versus 60.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Nemotron 3 Super 120B A12B has the edge for instruction following in this comparison, averaging 86 versus 82. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Nemotron 3 Super 120B A12B has the edge for multilingual tasks in this comparison, averaging 81.5 versus 80.1. 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.