NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 — Benchmarks

Benchmark scores for NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 aggregated from public leaderboards (8 boards), with how it ranks among open models and how it compares with its nearest neighbours. See hardware requirements for what you need to run it.

No llmrun Composite Score for NVIDIA Nemotron 3.5 Lightning 30B A3B BF16: the score is only published for a model measured on at least 4 of the boards in the score panel, spanning at least 2 benchmark categories and including a reasoning or coding board — or on 3 boards that narrow its score to a 90% range of at most 15.6 points. Either way the results must come from at least two different benchmarks. Its individual scores below stand on their own — see how the llmrun Composite Score gets calculated.

NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 reasoning benchmarks

Multi-step logic and problem-solving — can the model think through a hard problem rather than recall an answer.

LiveBench 2026 Reasoning
LiveBench 2026 Reasoning measures logical, multi-step problem solving. It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
42.9
42.9
median 79.6open leader 90.7
Overall best: Gemini 4 Argon 95.1
lowest · #19 of 19 open · #55 of 55 all
#19 of 19
#55 of 55
Independent
LiveBench · Oct 2026

Other results (2)leaderboard-only, not part of the llmrun Score

Leaderboard-only, not part of the llmrun Score

LiveBench 2026 Browser
LiveBench 2026 Browser measures tasks a model completes by operating a web browser. It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
0.0
0.0
median 16.0open leader 92.0
Overall best: Claude Fable 5.1 100.0
11th percentile · #16 of 19 open · #52 of 55 all
#16 of 19
#52 of 55
Independent
LiveBench · Oct 2026
LiveBench 2026 Data Analysis
LiveBench 2026 Data Analysis measures questions answered by working with tables and structured data. It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
43.1
43.1
median 72.3open leader 79.5
Overall best: Gemini 4 Argon 85.2
lowest · #19 of 19 open · #55 of 55 all
#19 of 19
#55 of 55
Independent
LiveBench · Oct 2026

NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 coding benchmarks

Writing, editing, and fixing real code — measured by whether the resulting program actually runs and passes tests.

LiveBench 2026 Coding
LiveBench 2026 Coding measures whether a model writes correct code for programming problems. It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
22.6
22.6
median 73.6open leader 96.0
Overall best: Claude Fable 5 98.3
lowest · #19 of 19 open · #55 of 55 all
#19 of 19
#55 of 55
Independent
LiveBench · Oct 2026
LiveBench 2026 Long-Horizon
LiveBench 2026 Long-Horizon measures multi-step tasks that a model has to carry through many steps to finish. It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
8.3
8.3
median 27.9open leader 50.9
Overall best: Claude Opus 5.5 85.0
lowest · #19 of 19 open · #55 of 55 all
#19 of 19
#55 of 55
Independent
LiveBench · Oct 2026

Other results (1)leaderboard-only, not part of the llmrun Score

Leaderboard-only, not part of the llmrun Score

LiveBench 2026 Design
LiveBench 2026 Design measures layout-design tasks (LiveBench's design_layout task). It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
43.9
43.9
median 70.7open leader 83.4
Overall best: Claude Opus 5.5 86.9
lowest · #19 of 19 open · #55 of 55 all
#19 of 19
#55 of 55
Independent
LiveBench · Oct 2026

NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 knowledge benchmarks

Breadth and depth of factual knowledge across many subjects, paired with the reasoning to apply it.

LiveBench 2026 Research
LiveBench 2026 Research measures finding and combining information to answer research questions. It belongs to the 2026 LiveBench release (first snapshot September 2, 2026), a redesigned LiveBench in which each of seven categories is scored by a single task and questions are refreshed to limit training-set contamination. It is a different test from the original LiveBench boards, so the scores are not comparable.
40.0
40.0
median 70.9open leader 86.8
Overall best: Claude Opus 5 88.9
6th percentile · #18 of 19 open · #54 of 55 all
#18 of 19
#54 of 55
Independent
LiveBench · Oct 2026

NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 instruction following benchmarks

How precisely a model obeys explicit, verifiable instructions — format, length, and content constraints — and, more broadly, how much people prefer its responses head-to-head in blind human voting.

LMArena Text
Arena (arena.ai, formerly LMArena / Chatbot Arena) ranks models by millions of blind, head-to-head human votes on real prompts. The Arena Score shown here is a Bradley-Terry rating computed with Arena's default style control, so higher means people preferred that model's answers more often — it's a relative rating, not a percentage, so compare it only to other models on this board.
1353.3
1353.3
median 1321.4open leader 1488.2
Overall best: Gemini 4 Carbon (High) 1527.5
60th percentile · #75 of 188 open · #208 of 408 all
#75 of 188
#208 of 408
Arena
Arena · Oct 2026

Scores aggregated from public benchmark sources (LiveBench: 7 boards, Arena: 1 board) — each linked from the benchmark pages. llmrun does not run these benchmarks. Percentiles and ranks are among open models in the llmrun catalogue; the median and leader marks refer to the same field.