Nemotron 3 Ultra 500B vs LFM2.5-1.2B-Thinking

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

Nemotron 3 Ultra 500B is clearly ahead on the aggregate, 64 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Nemotron 3 Ultra 500B's sharpest advantage is in reasoning, where it averages 77.2 against 38.4. The single biggest benchmark swing on the page is HumanEval, 66 to 17.

Nemotron 3 Ultra 500B gives you the larger context window at 10M, compared with 32K for LFM2.5-1.2B-Thinking.

Quick Verdict

Pick Nemotron 3 Ultra 500B if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

62.8

LFM2.5-1.2B-Thinking

34.1

63
Terminal-Bench 2.0
34
69
BrowseComp
37
58
OSWorld-Verified
32

Coding

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

43.8

LFM2.5-1.2B-Thinking

8.2

66
HumanEval
17
42
SWE-bench Verified
10
41
LiveCodeBench
9
47
SWE-bench Pro
7

Multimodal & Grounded

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

66.9

LFM2.5-1.2B-Thinking

32.4

61
MMMU-Pro
27
74
OfficeQA Pro
39

Reasoning

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

77.2

LFM2.5-1.2B-Thinking

38.4

71
SimpleQA
29
69
MuSR
31
85
BBH
67
81
LongBench v2
39
85
MRCRv2
42

Knowledge

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

57

LFM2.5-1.2B-Thinking

27

74
MMLU
27
73
GPQA
26
71
SuperGPQA
24
69
OpenBookQA
22
73
MMLU-Pro
51
15
HLE
2
67
FrontierScience
31

Instruction Following

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

84

LFM2.5-1.2B-Thinking

72

84
IFEval
72

Multilingual

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

79.7

LFM2.5-1.2B-Thinking

60.7

81
MGSM
62
79
MMLU-ProX
60

Mathematics

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

78

LFM2.5-1.2B-Thinking

42.3

74
AIME 2023
28
76
AIME 2024
30
75
AIME 2025
29
70
HMMT Feb 2023
24
72
HMMT Feb 2024
26
71
HMMT Feb 2025
25
73
BRUMO 2025
27
84
MATH-500
61

Frequently Asked Questions

Which is better, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B is ahead overall, 64 to 33. The biggest single separator in this matchup is HumanEval, where the scores are 66 and 17.

Which is better for knowledge tasks, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for knowledge tasks in this comparison, averaging 57 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for coding in this comparison, averaging 43.8 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for math in this comparison, averaging 78 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for reasoning in this comparison, averaging 77.2 versus 38.4. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for agentic tasks in this comparison, averaging 62.8 versus 34.1. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for multimodal and grounded tasks in this comparison, averaging 66.9 versus 32.4. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for instruction following in this comparison, averaging 84 versus 72. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Nemotron 3 Ultra 500B or LFM2.5-1.2B-Thinking?

Nemotron 3 Ultra 500B has the edge for multilingual tasks in this comparison, averaging 79.7 versus 60.7. Inside this category, MGSM 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.