Model comparison
Nemotron 3.5 Lightning vs Qwen2.5 72B Instruct
Nemotron 3.5 Lightning is the stronger model overall, scoring 39.3 to 31.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Nemotron 3.5 Lightning scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3.5 Lightning leads 34.7 to 18.1.
- Nemotron 3.5 Lightning is cheaper at $0.06 / $0.16 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Nemotron 3.5 Lightning accepts more context: 262K tokens versus 131K.
Side by side
| Nemotron 3.5 Lightning | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 39.3 | 31.5 |
| Released | 2026-08-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.06 | $1.40 |
| Output $ / M tokens | $0.16 | $5.60 |
| Results tracked | 18 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 39.6 (#143), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1370 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Nemotron 3.5 Lightning: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 25.7 (#128), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 34.7 (#156), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1355 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 36.9 (#154), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1354 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 44.0 (#175), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1292 | 1252 |
| LMArena Chinese | 1356 | 1272 |
| LMArena French | 1369 | 1279 |
| LMArena German | 1280 | 1234 |
| LMArena Japanese | 1213 | 1180 |
| LMArena Korean | 1233 | 1188 |
| LMArena Russian | 1257 | 1264 |
| LMArena Spanish | 1321 | 1255 |
Instruction Following Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 69.8 (#166), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1317 | 1254 |
| IFEval | — | 80.6% |
Long Context Too close to call
Nemotron 3.5 Lightning: 39.9 (#160), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1312 | 1282 |
Writing & Preference Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 48.5 (#198), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Nemotron 3.5 Lightning | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1324 | 1269 |
| LMArena Creative Writing | 1254 | 1221 |
| LMArena Multi-Turn | 1327 | 1272 |
| EQ-Bench Creative Writing | 1280 | — |
| WildBench | — | 80.2% |
Frequently asked questions
Is Nemotron 3.5 Lightning better than Qwen2.5 72B Instruct?
Nemotron 3.5 Lightning is the stronger model overall, scoring 39.3 to 31.5 on the Noometry Index.
Which is cheaper, Nemotron 3.5 Lightning or Qwen2.5 72B Instruct?
Nemotron 3.5 Lightning is cheaper. It lists at $0.06 per million input tokens and $0.16 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Nemotron 3.5 Lightning or Qwen2.5 72B Instruct better for coding?
Nemotron 3.5 Lightning scores higher on coding benchmarks: 39.6 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3.5 Lightning does, with 262K tokens against 131K.
How many benchmarks do Nemotron 3.5 Lightning and Qwen2.5 72B Instruct share?
17 benchmarks have published results for both models. Nemotron 3.5 Lightning has 18 scored results on Noometry and Qwen2.5 72B Instruct has 43.