ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek V3.2vsNVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4

DeepSeek V3.2 leads 5 of 5 shared benchmarks. NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
5 – 0
DeepSeek V3.2 leads
Cheaper per token
list price, input + output
Larger context
NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4
1M tokens
Provider uptime (30d)
100% · 100%
DeepSeek · NVIDIA
DeepSeek V3.2
DeepSeek · released 2025-12-01
text
Context
131K
Max out
66K
Input /1M
Output /1M
Cached /1M
Scores
8 · 7 core
NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4
NVIDIA · released 2026-08-11
text
Context
1M
Max out
Input /1M
Output /1M
Cached /1M
Scores
7 · 5 core
Quality

Benchmark matrix

BenchmarkDeepSeek V3.2NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4ΔEdge
Reported by both · 5
SWE-bench Verified73.1% 52.8% +20.3 ptDeepSeek V3.2
GPQA Diamond82.4% 75.57% +6.8 ptDeepSeek V3.2
MMLU-Pro85% 81.62% +3.4 ptDeepSeek V3.2
Humanity's Last Exam (no tools)25.1% 10.47% +14.6 ptDeepSeek V3.2
LMArena Elo1424.8 1330.7 +94.1DeepSeek V3.2
Only DeepSeek V3.2 reports · 2
AIME 202593.1% not reported
AIME 202694.2% matharenanot reported
Only NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 reports · 2
BrowseCompnot reported36.81%
Terminal-Bench 2.1not reported23.46%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek V3.2 minus NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecDeepSeek V3.2NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4Edge
Context window131K tokens1M tokensNVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4
Max output66K tokens
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
ModalitiestexttextTie
Released2025-12-012026-08-11
Cited benchmark scores87
Reliability

Provider status

All providers
More matchups

NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek V3.2 and NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.