Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Nemotron 3 Nano 30B is clearly ahead on the aggregate, 45 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Nemotron 3 Nano 30B's sharpest advantage is in mathematics, where it averages 63.7 against 37. The single biggest benchmark swing on the page is HumanEval, 49 to 14. LFM2.5-1.2B-Instruct does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
Pick Nemotron 3 Nano 30B if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if instruction following is the priority.
Nemotron 3 Nano 30B
39.6
LFM2.5-1.2B-Instruct
25.7
Nemotron 3 Nano 30B
22
LFM2.5-1.2B-Instruct
7.2
Nemotron 3 Nano 30B
45.2
LFM2.5-1.2B-Instruct
32.4
Nemotron 3 Nano 30B
54
LFM2.5-1.2B-Instruct
32.1
Nemotron 3 Nano 30B
43.8
LFM2.5-1.2B-Instruct
26
Nemotron 3 Nano 30B
78
LFM2.5-1.2B-Instruct
80
Nemotron 3 Nano 30B
71.8
LFM2.5-1.2B-Instruct
60.7
Nemotron 3 Nano 30B
63.7
LFM2.5-1.2B-Instruct
37
Nemotron 3 Nano 30B is ahead overall, 45 to 30. The biggest single separator in this matchup is HumanEval, where the scores are 49 and 14.
Nemotron 3 Nano 30B has the edge for knowledge tasks in this comparison, averaging 43.8 versus 26. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Nemotron 3 Nano 30B has the edge for coding in this comparison, averaging 22 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Nemotron 3 Nano 30B has the edge for math in this comparison, averaging 63.7 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Nemotron 3 Nano 30B has the edge for reasoning in this comparison, averaging 54 versus 32.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Nemotron 3 Nano 30B has the edge for agentic tasks in this comparison, averaging 39.6 versus 25.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Nemotron 3 Nano 30B has the edge for multimodal and grounded tasks in this comparison, averaging 45.2 versus 32.4. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Instruct has the edge for instruction following in this comparison, averaging 80 versus 78. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Nemotron 3 Nano 30B has the edge for multilingual tasks in this comparison, averaging 71.8 versus 60.7. 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.