Nemotron 3 Ultra vs Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct costs 2.4x less per output token than Nemotron 3 Ultra ($1.00 vs $2.40 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- 30.0
- Overall
- 53.1
- Output $/M
- $2.40
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.00
Nemotron 3 Ultra or Qwen2.5 VL 72B Instruct: which to pick
Only Nemotron 3 Ultra has a coding score, 30.0 on the Vibe Coding Index; Qwen2.5 VL 72B Instruct has none, so the two cannot be ranked on coding.
Pick Qwen2.5 VL 72B Instruct for output tokens 2.4x cheaper ($1.00 vs $2.40 per million).
No benchmark has tested both yet. Nemotron 3 Ultra has results on AA Coding Index, LiveCodeBench (Vals AI) and SWE-bench Verified (Vals AI); Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead.
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
Only Nemotron 3 Ultra has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Nemotron 3 Ultra has a AA Intelligence Index result, 22.9.
Directional only
Agentic work
AA Agentic Index
No call
Only Nemotron 3 Ultra has a AA Agentic Index result, 20.1.
Directional only
Reasoning
GPQA Diamond
No call
Only Nemotron 3 Ultra has a GPQA Diamond result, 86.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Nemotron 3 Ultra has a MMLU Pro result, 85.8%.
Directional only
Web design
Design Arena: websites
No call
Only Nemotron 3 Ultra has a Design Arena: websites result, 1145.
Directional only
Long documents
Listed context window
Nemotron 3 Ultra
Nemotron 3 Ultra takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 VL 72B Instruct
Nemotron 3 Ultra $0.0018, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices
At a glance
- Coding index
- Nemotron 3 Ultra 30.0 from 3 benchmarks, Qwen2.5 VL 72B Instruct not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Nemotron 3 Ultra $2.40 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 2.4x apart.
- Context window
- Nemotron 3 Ultra takes 262K tokens, Qwen2.5 VL 72B Instruct 128K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index13 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Coding Index | 49.3 | Not measured | Only Nemotron 3 Ultra measured |
| LiveCodeBench (Vals AI) | 86.0% | Not measured | Only Nemotron 3 Ultra measured |
| SWE-bench Verified (Vals AI) | 69.0% | Not measured | Only Nemotron 3 Ultra measured |
| Vibe Code Bench (Vals AI) | 7.6% | Not measured | Only Nemotron 3 Ultra measured |
| Code migration (Vals AI) | 4.9% | Not measured | Only Nemotron 3 Ultra measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Nemotron 3 Ultra measured |
| Terminal-Bench 2.1 (Vals AI) | 50.9% | Not measured | Only Nemotron 3 Ultra measured |
| SciCode | 40.3% | Not measured | Only Nemotron 3 Ultra measured |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | Not measured | Only Nemotron 3 Ultra measured |
| FrontierCode | 13.6% | Not measured | Only Nemotron 3 Ultra measured |
| WeirdML | 43.5% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: coding | 1468 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: software and IT | 1468 | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.9 | Not measured | Only Nemotron 3 Ultra measured |
| Epoch Capabilities Index | 146.0 | Not measured | Only Nemotron 3 Ultra measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Agentic Index | 20.1 | Not measured | Only Nemotron 3 Ultra measured |
| Finance Agent (Vals AI) | 37.7% | Not measured | Only Nemotron 3 Ultra measured |
| Legal Research Bench (Vals AI) | 15.4% | Not measured | Only Nemotron 3 Ultra measured |
| Excel Modeling Benchmark (Vals AI) | 31.7% | Not measured | Only Nemotron 3 Ultra measured |
| τ²-Bench Telecom | 83.3% | Not measured | Only Nemotron 3 Ultra measured |
| APEX-Agents | 22.7% | Not measured | Only Nemotron 3 Ultra measured |
| OSWorld | Not measured | 5.0% | Only Qwen2.5 VL 72B Instruct measured |
| MCP Atlas | 63.1% | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond | 86.1% | Not measured | Only Nemotron 3 Ultra measured |
| GPQA Diamond (Artificial Analysis run) | 86.7% | Not measured | Only Nemotron 3 Ultra measured |
| Humanity's Last Exam (Artificial Analysis run) | 28.4% | Not measured | Only Nemotron 3 Ultra measured |
| GPQA Diamond (Epoch AI run) | 85.4% | Not measured | Only Nemotron 3 Ultra measured |
| Mystery game puzzles | 20.0% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: hard prompts | 1452 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: expert | 1472 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: hard prompts in English | 1453 | Not measured | Only Nemotron 3 Ultra measured |
| Kagi LLM Benchmark | Not measured | 36.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| OTIS Mock AIME | 86.7% | Not measured | Only Nemotron 3 Ultra measured |
| ProofBench | 2.0% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: math | 1457 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: mathematical work | 1461 | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro | 85.8% | Not measured | Only Nemotron 3 Ultra measured |
| LegalBench (Vals AI) | 82.1% | Not measured | Only Nemotron 3 Ultra measured |
| CorpFin (Vals AI) | 65.5% | Not measured | Only Nemotron 3 Ultra measured |
| TaxEval (Vals AI) | 73.1% | Not measured | Only Nemotron 3 Ultra measured |
| MedCode (Vals AI) | 38.6% | Not measured | Only Nemotron 3 Ultra measured |
| GeoBench | Not measured | 62.0% | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: science | 1465 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: medicine and healthcare | 1456 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: legal and government | 1452 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: business and finance | 1434 | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1145 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: UI components | 1135 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: game dev | 1138 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: data viz | 1141 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: 3D | 1131 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: all code categories | 1146 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: SVG | 1069 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: ASCII art | 1100 | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards measured
| Benchmark | Nemotron 3 Ultra | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| IFBench | 81.4% | Not measured | Only Nemotron 3 Ultra measured |
| Long context reasoning (AA-LCR) | 79.3% | Not measured | Only Nemotron 3 Ultra measured |
| DTBench | 90.1% | Not measured | Only Nemotron 3 Ultra measured |
| LMCA | 36.9% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text | 1445 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: instruction following | 1418 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: creative writing | 1399 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Vision | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: English | 1455 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: non-English | 1427 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: Chinese | 1497 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: German | 1472 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: Korean | 1384 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: French | 1472 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: Spanish | 1455 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: Russian | 1417 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: Polish | 1385 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: multi-turn | 1411 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: longer queries | 1437 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: writing and language | 1406 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: entertainment and media | 1397 | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Vision: English | Not measured | 1115 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: Chinese | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 25 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
Qwen2.5 VL 72B Instruct costs less
Repository review
50K input + 3K output tokens
Nemotron 3 Ultra costs less
Agent loop
200K input + 10K output tokens
Nemotron 3 Ultra 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 Ultra | Qwen2.5 VL 72B Instruct |
|---|---|---|
| Maker | NVIDIA | Qwen |
| Weights | Open weights | Open weights |
| Released | June 4, 2026 | February 1, 2025 |
| Context window | 262K | 128K |
| Input $/Mtok | $0.60 | $0.80 |
| Output $/Mtok | $2.40 | $1.00 |
| Coding index | 30.0 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nemotron 3 Ultra better than Qwen2.5 VL 72B Instruct for coding?
Only Nemotron 3 Ultra has a coding score, 30.0 on the Vibe Coding Index; Qwen2.5 VL 72B Instruct has none, so the two cannot be ranked on coding. Pick Qwen2.5 VL 72B Instruct for output tokens 2.4x cheaper ($1.00 vs $2.40 per million).
Which is cheaper, Nemotron 3 Ultra or Qwen2.5 VL 72B Instruct?
Nemotron 3 Ultra costs $0.60 per million input tokens and $2.40 per million output tokens; Qwen2.5 VL 72B Instruct costs $0.80 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Nemotron 3 Ultra or Qwen2.5 VL 72B Instruct?
Nemotron 3 Ultra, with 262K tokens against 128K.
Has any benchmark tested both Nemotron 3 Ultra and Qwen2.5 VL 72B Instruct?
No benchmark has tested both yet. Nemotron 3 Ultra has results on AA Coding Index, LiveCodeBench (Vals AI) and SWE-bench Verified (Vals AI); Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead. Data as of October 22, 2026.