Granite 4.2 30B vs Nemotron 3.5 Super VL
Full profiles: Granite 4.2 30B (IBM) and Nemotron 3.5 Super VL (NVIDIA): every benchmark, price and rank.
Updated · Data from 6 sources
As of 16 Nov 2026, Granite 4.2 30B and Nemotron 3.5 Super VL are neck and neck on quality (45.8 vs 45.8 on the BenchLeader Index, inside the ±9.8 margin), and they cost about the same at $0.283 vs $0.275 per 1M tokens blended. Choose Granite 4.2 30B for coding (52 vs 34); choose Nemotron 3.5 Super VL for long context (59 vs 48), knowledge (43 vs 38), and reasoning (37 vs 35).
Key facts (as of 16 Nov 2026)
- Granite 4.2 30B scores 45.8 on the BenchLeader Index and Nemotron 3.5 Super VL scores 45.8 (BenchLeader, 16 Nov 2026).
- Granite 4.2 30B costs $0.283 per 1M tokens blended (list price, 16 Nov 2026).
- Nemotron 3.5 Super VL costs $0.275 per 1M tokens blended (list price, 16 Nov 2026).
- Of the 18 benchmarks both models have, Nemotron 3.5 Super VL leads 15 (BenchLeader, 16 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Granite 4.2 30B | 52 vs 34 category score; SciCode (AA) 37.9% vs 47.8% | High |
| Reasoning | Nemotron 3.5 Super VL | 37 vs 35 category score; HLE-Diamond (AA) 8.8% vs 4.3% | Medium |
| Knowledge | Nemotron 3.5 Super VL | 43 vs 38 category score; AA-Omniscience v1.1 -2.9 vs -12.4 | Medium |
| Long documents | Nemotron 3.5 Super VL | 59 vs 48 category score; AA-LCR v1.1 69.0% vs 49.0% | High |
| Chat quality (human preference) | – | Only Granite 4.2 30B has an Arena rating (50 category score) | Not comparable |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Granite 4.2 30B and Nemotron 3.5 Super VL are neck and neck on quality (45.8 vs 45.8, within the ±9.8 margin).
- Granite 4.2 30B is stronger in coding.
- Nemotron 3.5 Super VL is stronger in knowledge, long context, reasoning.
- They cost about the same ($0.275 per 1M blended).
At a glance
| Spec | Granite 4.2 30B | Nemotron 3.5 Super VL |
|---|---|---|
| Developer | IBM | NVIDIA |
| Released | 25 Aug 2026 | 15 Oct 2026 |
| Context window (tokens) | 131,072 | 1,048,576 |
| Compared at | Granite 4.2 30B | Nemotron 3.5 Super VL |
| Open weights | Yes | Yes |
| Price in / out / cached input per 1M | – | $0.200 / $0.500 / $0.020 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Granite 4.2 30B | Nemotron 3.5 Super VL | Leader |
|---|---|---|---|
| Reasoning | 34.9 | 36.5 | Nemotron 3.5 Super VL |
| Coding | 51.7 | 34.4 | Granite 4.2 30B |
| Agents & tools | 42.2 | – | not comparable |
| Knowledge | 38.0 | 43.2 | Nemotron 3.5 Super VL |
| Human preference | 49.8 | – | not comparable |
| Long context | 48.4 | 58.9 | Nemotron 3.5 Super VL |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Multimodal, Human preference.
Where sources disagree
Across the 18 benchmarks both have, Granite 4.2 30B leads 1, Nemotron 3.5 Super VL leads 15 and 2 are tied.
| Overall index | Granite 4.2 30B | Nemotron 3.5 Super VL | Leader |
|---|---|---|---|
| BenchLeader Index | 45.8 | 45.8 | neck and neck |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Granite 4.2 30B | Nemotron 3.5 Super VL |
|---|---|---|
| Blended price per 1M tokens | – | $0.275 |
| Input / output per 1M | – / – | $0.200 / $0.500 |
| Cached input per 1M | – | $0.020 |
| Price per task: chat reply | – | $0.0002 |
| Price per task: summarize a 30-page report | – | $0.0027 |
| Price per task: code edit | – | $0.0020 |
| Price per task: agentic coding session | – | $0.014 |
| Price per task: structured extraction | – | $0.0005 |
| Agentic coding session, input mostly cached | – | $0.0059 |
| Cost per benchmark task (AA Index) | – | $0.557 |
| Output tokens per task (AA Index) | – | 81k |
| Of which reasoning | – | 56k |
| Time per task (AA Index) | – | 5 min |
| Output speed | – | 271 tok/s |
| Time to first answer | – | 13.7 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 36.4 s |
Each model is compared at its best-ranked reasoning-effort setting. Granite 4.2 30B scores 45.8. Nemotron 3.5 Super VL scores 45.8 and takes 14 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
43 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Granite 4.2 30B | Nemotron 3.5 Super VL |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 45.8 | 45.8 |
| Agents & tools score | BenchLeader | 42.2 | – |
| Coding score | BenchLeader | 51.7 | 34.4 |
| Human preference score | BenchLeader | 49.8 | – |
| Knowledge score | BenchLeader | 38.0 | 43.2 |
| Long context score | BenchLeader | 48.4 | 58.9 |
| Reasoning score | BenchLeader | 34.9 | 36.5 |
| Blended price $/M | BenchLeader | – | $0.275 |
| Output speed | BenchLeader | – | 271 tok/s |
| Time to first answer | BenchLeader | – | 13.7 s |
| Context window | BenchLeader | 131,072 tokens | 1,048,576 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | 1366 | – |
| GPQA Diamond (AA) | Artificial Analysis | 64.4% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 11.2% | 30.7% |
| HLE-Diamond (AA) | Artificial Analysis | 4.3% | 8.8% |
| ARC-AGI-1 | ARC Prize | – | 2.0%† |
| ARC-AGI-2 | ARC Prize | – | 0.8%† |
| CritPt | Artificial Analysis | 0.3% | 10.6% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 1.5% | 13.5% |
| Arena Expert | Arena (LMArena) | 1398 | – |
| Coding | |||
| Arena Coding | Arena (LMArena) | 1398 | – |
| SciCode (AA) | Artificial Analysis | 37.9% | 47.8% |
| SWE Atlas v1.1 | Scale AI SEAL | – | 24.8% |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 26.6% |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 27.8% |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 20.0% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 0.0% | 0.0% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 26.6% | – |
| Design Arena Website | Design Arena | – | 1160 |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 25.5% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 6.1% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 0.3%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 3.7% | 33.1% |
| GDPval-AA v2.1 | Artificial Analysis | 583 | 1162 |
| τ³-Banking (AA) | Artificial Analysis | 14.4% | – |
| AutomationBench | Artificial Analysis | 1.5% | 14.8% |
Show all 43 benchmarks
| Metric | Publisher | Granite 4.2 30B | Nemotron 3.5 Super VL |
|---|---|---|---|
| Agents & tools | |||
| GDP.pdf (AA) | Artificial Analysis | 1.8% | 8.0% |
| AA-Briefcase v1.1 | Artificial Analysis | 395 | 999 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 0.0% | 0.0% |
| Knowledge | |||
| AA-Omniscience v1.1 | Artificial Analysis | -12.4 | -2.9 |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 11.2% | 21.2% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 73.3% | 69.5% |
| Instruction following | |||
| Arena Instruction Following | Arena (LMArena) | 1342 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1340 | – |
| Arena Creative Writing | Arena (LMArena) | 1263 | – |
| Arena Multi-turn | Arena (LMArena) | 1319 | – |
| Arena Longer Queries | Arena (LMArena) | 1347 | – |
| Multimodal | |||
| Humanity's Sixth Sense | Scale AI SEAL | – | 24.7%† |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 49.0% | 69.0% |
| MLCR | Artificial Analysis | – | 13.3% |
| Composite | |||
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 13.6 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 12.7 | 26.5 |
| AA Progress Index v1 | Artificial Analysis | 225.3 | 283.9 |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 72.2 | 83.3 |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
What changed
- Nemotron 3.5 Super VL: Nemotron 3.5 Super VL cached input price moved from $0.060/M to $0.020/M (67% down).
- Nemotron 3.5 Super VL: Nemotron 3.5 Super VL input price moved from $0.18/M to $0.20/M (11% up); Nemotron 3.5 Super VL cost per task moved from $0.52/M to $0.56/M (7% up).
- Nemotron 3.5 Super VL: BenchLeader Index 48.9 → 45.8.
- Nemotron 3.5 Super VL: BenchLeader Index 45.7 → 48.9.
- Nemotron 3.5 Super VL: 1 new result (HiL-Bench); 1 score revision.
- Nemotron 3.5 Super VL: Nemotron 3.5 Super VL input price moved from $0.20/M to $0.18/M (10% down).
- Granite 4.2 30B: 1 new result (Terminal-Bench-Science 0.1 (AA)).
- Granite 4.2 30B: BenchLeader Index 46.6 → 45.9.
- Nemotron 3.5 Super VL: BenchLeader Index 45.0 → 45.7.
- Granite 4.2 30B: 1 new result (CritPt v2 hard subset (AA)).
Related comparisons
- Nemotron 3.5 Super VL vs Command A+
- Nemotron 3.5 Super VL vs Beam 1.0
- Nemotron 3.5 Super VL vs Mistral Large 3
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Granite 4.2 30B vs Nemotron 3.5 Super VL: questions
- Is Granite 4.2 30B better than Nemotron 3.5 Super VL?
- Granite 4.2 30B and Nemotron 3.5 Super VL are neck and neck on quality (45.8 vs 45.8, within the ±9.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
- Granite 4.2 30B vs Nemotron 3.5 Super VL: which is cheaper, and will that change?
- Nemotron 3.5 Super VL is cheaper today: $0.275 against $0.283 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Granite 4.2 30B or Nemotron 3.5 Super VL better for coding?
- Granite 4.2 30B scores higher in coding (52 vs 34 on the category index, where 50 is average).
- Which is better for long documents?
- Nemotron 3.5 Super VL scores higher on long-context benchmarks (59 vs 48). Nemotron 3.5 Super VL accepts more context: 1,048,576 against 131,072 tokens for Granite 4.2 30B.
- Do independent benchmarks agree on Granite 4.2 30B vs Nemotron 3.5 Super VL?
- Across the 18 benchmarks both have, Granite 4.2 30B leads 1, Nemotron 3.5 Super VL leads 15 and 2 are tied.
More questions (1)
- When was Nemotron 3.5 Super VL released?
- Nemotron 3.5 Super VL was released on 15 Oct 2026.