Model comparison
DeepSeek-V3 vs Nemotron 3.5 Lightning
DeepSeek-V3 and Nemotron 3.5 Lightning score almost the same on the Noometry Index (39.5 vs 40.0), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 18 benchmarks with published results for both. DeepSeek-V3 scores higher in 4 categories and Nemotron 3.5 Lightning in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3 leads 57.4 to 48.5.
- Nemotron 3.5 Lightning is cheaper at $0.05 / $0.20 per million input/output tokens, against $0.24 / $0.90 for DeepSeek-V3.
- Nemotron 3.5 Lightning accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3 | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 39.5 | 40.0 |
| Released | 2024-12-26 | 2026-08-11 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 164K | 262K |
| Input $ / M tokens | $0.24 | $0.05 |
| Output $ / M tokens | $0.90 | $0.20 |
| Results tracked | 60 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 42.3 (#106), Nemotron 3.5 Lightning: 40.4 (#141)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1368 | 1375 |
| Aider Polyglot | 55.1% | — |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Nemotron 3.5 Lightning: —
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| METR Time Horizons | 49.6% | — |
Reasoning Nemotron 3.5 Lightning leads
DeepSeek-V3: 20.5 (#236), Nemotron 3.5 Lightning: 26.8 (#127)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1365 | 1337 |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.94 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math Nemotron 3.5 Lightning leads
DeepSeek-V3: 32.1 (#219), Nemotron 3.5 Lightning: 37.5 (#155)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1373 | 1359 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Too close to call
DeepSeek-V3: 37.5 (#155), Nemotron 3.5 Lightning: 37.5 (#154)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1351 | 1356 |
| GPQA Diamond | 67.6% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual DeepSeek-V3 leads
DeepSeek-V3: 48.5 (#143), Nemotron 3.5 Lightning: 44.0 (#180)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1358 | 1295 |
| LMArena Chinese | 1391 | 1359 |
| LMArena French | 1385 | 1366 |
| LMArena German | 1374 | 1282 |
| LMArena Japanese | 1333 | 1206 |
| LMArena Korean | 1319 | 1238 |
| LMArena Russian | 1373 | 1253 |
| LMArena Spanish | 1358 | 1345 |
Instruction Following DeepSeek-V3 leads
DeepSeek-V3: 72.8 (#130), Nemotron 3.5 Lightning: 69.6 (#170)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1345 | 1318 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context Nemotron 3.5 Lightning leads
DeepSeek-V3: 34.0 (#253), Nemotron 3.5 Lightning: 39.9 (#165)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1352 | 1314 |
| Fiction.LiveBench | 50% | — |
Writing & Preference DeepSeek-V3 leads
DeepSeek-V3: 57.4 (#130), Nemotron 3.5 Lightning: 48.5 (#201)
| Benchmark | DeepSeek-V3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1375 | 1327 |
| LMArena Creative Writing | 1364 | 1254 |
| EQ-Bench Creative Writing | 1472 | 1280 |
| LMArena Multi-Turn | 1389 | 1328 |
| Short-Story Creative Writing | 77% | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Nemotron 3.5 Lightning?
DeepSeek-V3 and Nemotron 3.5 Lightning score almost the same on the Noometry Index (39.5 vs 40.0), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3 or Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is cheaper. It lists at $0.05 per million input tokens and $0.20 per million output tokens; DeepSeek-V3 lists at $0.24 and $0.90.
Is DeepSeek-V3 or Nemotron 3.5 Lightning better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 40.4 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3.5 Lightning does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3 and Nemotron 3.5 Lightning share?
18 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Nemotron 3.5 Lightning has 18.