Nemotron 3 Nano 30B A3B vs Qwen2.5 72B Instruct
Nemotron 3 Nano 30B A3B leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 8.9 to 7.7, and Nemotron 3 Nano 30B A3B costs 1.8x less per output token ($0.22 vs $0.40 per million). Updated October 23, 2026; 37 benchmarks have a result for both.
Nemotron 3 Nano 30B A3B or Qwen2.5 72B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Nemotron 3 Nano 30B A3B for output tokens 1.8x cheaper ($0.22 vs $0.40 per million) and a larger context window (262K against 33K tokens).
- Shared results
- 37
- Nemotron 3 Nano 30B A3B only
- 5
- Qwen2.5 72B Instruct only
- 16
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B leads, 8.9 against 7.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Nemotron 3 Nano 30B A3B has a AA Agentic Index result, 1.0.
Directional only
Long documents
Listed context window
Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B takes 262K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B $0.0002, Qwen2.5 72B Instruct $0.0006 per turn.
List prices
At a glance
- Coding index
- Nemotron 3 Nano 30B A3B not benchmarked, Qwen2.5 72B Instruct not benchmarked.
- Widest category
- Math, 45.7 points apart on average over 4 shared benchmarks.
- Widest single gap
- AA Math Index: Nemotron 3 Nano 30B A3B 91.0 against Qwen2.5 72B Instruct 14.0, 77.0 points apart on a 0 to 100 scale.
- Output price
- Nemotron 3 Nano 30B A3B $0.22 against Qwen2.5 72B Instruct $0.40 per million output tokens, 1.8x apart.
- Context window
- Nemotron 3 Nano 30B A3B takes 262K tokens, Qwen2.5 72B Instruct 33K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Nemotron 3 Nano 30B A3B | Bars | Qwen2.5 72B Instruct | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 4 | 0 | ||
| Knowledge | 5 | 0 | ||
| General | 17 | 0 | ||
| All shared boards | 37 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Coding Index | 14.4 | Not measured | Only Nemotron 3 Nano 30B A3B measured |
| LiveCodeBench (Artificial Analysis run) | 74.1% | 27.6% | Nemotron 3 Nano 30B A3B |
| SciCode | 30.6% | Not measured | Only Nemotron 3 Nano 30B A3B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 13.6% | 4.5% | Nemotron 3 Nano 30B A3B |
| WeirdML | Not measured | 16.0% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: coding | 1378 | 1292 | Nemotron 3 Nano 30B A3B |
| LMArena Text: software and IT | 1382 | 1292 | Nemotron 3 Nano 30B A3B |
| Neither model has a result on the other 36 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 8.9 | 7.7 | Nemotron 3 Nano 30B A3B |
| Epoch Capabilities Index | Not measured | 129.0 | Only Qwen2.5 72B Instruct measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Agentic Index | 1.0 | Not measured | Only Nemotron 3 Nano 30B A3B measured |
| τ²-Bench Telecom | 40.9% | 34.5% | Nemotron 3 Nano 30B A3B |
| METR time horizons | Not measured | 35.8% | Only Qwen2.5 72B Instruct measured |
| BALROG | Not measured | 16.2% | Only Qwen2.5 72B Instruct measured |
| TheAgentCompany | Not measured | 5.7% | Only Qwen2.5 72B Instruct measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 75.7% | 49.1% | Nemotron 3 Nano 30B A3B |
| Humanity's Last Exam (Artificial Analysis run) | 11.4% | 3.6% | Nemotron 3 Nano 30B A3B |
| GPQA Diamond (Epoch AI run) | Not measured | 49.1% | Only Qwen2.5 72B Instruct measured |
| BIG-Bench Hard | Not measured | 79.8% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: hard prompts | 1348 | 1270 | Nemotron 3 Nano 30B A3B |
| LMArena Text: expert | 1356 | 1245 | Nemotron 3 Nano 30B A3B |
| LMArena Text: hard prompts in English | 1376 | 1279 | Nemotron 3 Nano 30B A3B |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 91.0 | 14.0 | Nemotron 3 Nano 30B A3B |
| AIME 2025 (Artificial Analysis run) | 91.0% | 14.0% | Nemotron 3 Nano 30B A3B |
| OTIS Mock AIME | Not measured | 8.1% | Only Qwen2.5 72B Instruct measured |
| MATH level 5 | Not measured | 63.2% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: math | 1371 | 1283 | Nemotron 3 Nano 30B A3B |
| LMArena Text: mathematical work | 1375 | 1290 | Nemotron 3 Nano 30B A3B |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 79.4% | 72.0% | Nemotron 3 Nano 30B A3B |
| MMLU | Not measured | 85.3% | Only Qwen2.5 72B Instruct measured |
| AI2 Reasoning Challenge | Not measured | 94.5% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: science | 1353 | 1275 | Nemotron 3 Nano 30B A3B |
| LMArena Text: medicine and healthcare | 1349 | 1258 | Nemotron 3 Nano 30B A3B |
| LMArena Text: legal and government | 1341 | 1288 | Nemotron 3 Nano 30B A3B |
| LMArena Text: business and finance | 1345 | 1253 | Nemotron 3 Nano 30B A3B |
| Neither model has a result on the other 13 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| IFBench | 71.1% | 36.9% | Nemotron 3 Nano 30B A3B |
| Long context reasoning (AA-LCR) | 38.0% | Not measured | Only Nemotron 3 Nano 30B A3B measured |
| DTBench | Not measured | 62.9% | Only Qwen2.5 72B Instruct measured |
| LMCA | Not measured | 13.4% | Only Qwen2.5 72B Instruct measured |
| HellaSwag | Not measured | 84.8% | Only Qwen2.5 72B Instruct measured |
| WinoGrande | Not measured | 82.3% | Only Qwen2.5 72B Instruct measured |
| PIQA | Not measured | 82.6% | Only Qwen2.5 72B Instruct measured |
| LMArena Text | 1348 | 1269 | Nemotron 3 Nano 30B A3B |
| LMArena Text: instruction following | 1304 | 1254 | Nemotron 3 Nano 30B A3B |
| LMArena Text: creative writing | 1270 | 1221 | Nemotron 3 Nano 30B A3B |
| LMArena Text: English | 1378 | 1283 | Nemotron 3 Nano 30B A3B |
| LMArena Text: non-English | 1320 | 1252 | Nemotron 3 Nano 30B A3B |
| LMArena Text: Chinese | 1383 | 1273 | Nemotron 3 Nano 30B A3B |
| LMArena Text: German | 1348 | 1234 | Nemotron 3 Nano 30B A3B |
| LMArena Text: Japanese | 1269 | 1180 | Nemotron 3 Nano 30B A3B |
| LMArena Text: Korean | 1269 | 1188 | Nemotron 3 Nano 30B A3B |
| LMArena Text: French | 1396 | 1280 | Nemotron 3 Nano 30B A3B |
| LMArena Text: Spanish | 1376 | 1256 | Nemotron 3 Nano 30B A3B |
| LMArena Text: Russian | 1304 | 1264 | Nemotron 3 Nano 30B A3B |
| LMArena Text: Polish | 1302 | Not measured | Only Nemotron 3 Nano 30B A3B measured |
| LMArena Text: multi-turn | 1319 | 1272 | Nemotron 3 Nano 30B A3B |
| LMArena Text: longer queries | 1300 | 1281 | Nemotron 3 Nano 30B A3B |
| LMArena Text: writing and language | 1284 | 1247 | Nemotron 3 Nano 30B A3B |
| LMArena Text: entertainment and media | 1294 | 1211 | Nemotron 3 Nano 30B A3B |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Nemotron 3 Nano 30B A3B costs less
Repository review
50K input + 3K output tokens
Nemotron 3 Nano 30B A3B costs less
Agent loop
200K input + 10K output tokens
Nemotron 3 Nano 30B A3B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | NVIDIA Nemotron 3 Nano 30B A3B | Qwen2.5 72B Instruct |
|---|---|---|
| Maker | NVIDIA | Qwen |
| Weights | Open weights | Open weights |
| Released | December 14, 2025 | September 19, 2024 |
| Context window | 262K | 33K |
| Input $/Mtok | $0.055 | $0.36 |
| Output $/Mtok | $0.22 | $0.40 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nemotron 3 Nano 30B A3B better than Qwen2.5 72B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nemotron 3 Nano 30B A3B for output tokens 1.8x cheaper ($0.22 vs $0.40 per million) and a larger context window (262K against 33K tokens).
Which is cheaper, Nemotron 3 Nano 30B A3B or Qwen2.5 72B Instruct?
Nemotron 3 Nano 30B A3B costs $0.055 per million input tokens and $0.22 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, Nemotron 3 Nano 30B A3B or Qwen2.5 72B Instruct?
Nemotron 3 Nano 30B A3B, with 262K tokens against 33K.
How many benchmarks is the Nemotron 3 Nano 30B A3B vs Qwen2.5 72B Instruct comparison based on?
37 benchmarks have a result for both models as of October 23, 2026. Nemotron 3 Nano 30B A3B's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.