IBM Granite 4.2 30B vs Nemotron 3.5 Super VL (120B A12B): Specs & Benchmark Comparison

IBM Granite 4.2 30B is developed by IBM, while Nemotron 3.5 Super VL (120B A12B) comes from NVIDIA. IBM Granite 4.2 30B was released in August 2026, and Nemotron 3.5 Super VL (120B A12B) followed 2 months later in October 2026. Nemotron 3.5 Super VL (120B A12B) is the larger model at roughly 120 billion parameters, against 30 billion for IBM Granite 4.2 30B.

The two models share 8 published benchmarks. Nemotron 3.5 Super VL (120B A12B) leads on 7 of them, IBM Granite 4.2 30B on 1. The widest gaps are on Terminal-Bench 2.1, where Nemotron 3.5 Super VL (120B A12B) scores 66.7% against 29.2%; SWE-bench Multilingual, where Nemotron 3.5 Super VL (120B A12B) scores 67.7% against 41.9%. Averaged across everything we track, IBM Granite 4.2 30B sits at 62.4% and Nemotron 3.5 Super VL (120B A12B) at 60.9%.

Nemotron 3.5 Super VL (120B A12B) is available through an API at $0.20 per million input tokens with a 262K-token context window. We do not track a hosted API for IBM Granite 4.2 30B, so pricing and context cannot be compared directly.

CharacteristicIBM Granite 4.2 30BNemotron 3.5 Super VL (120B A12B)
CompanyIBMNVIDIA
Release DateAugust 25, 2026October 15, 2026
Parameters30B120B
MultimodalNoYes
Context (input)—262K
Context (output)—262K
Input Price / 1M—$0.20
Output Price / 1M—$1.00
Average Score62.4%60.9%
Benchmarks
Terminal-Bench 2.129.2%66.7%
SWE-bench Multilingual41.9%67.7%
GPQA66.4%89.5%
SWE-Bench Pro33.3%51.8%
SWE-Bench Verified57.0%71.1%
LiveCodeBench v675.8%88.2%
SciCode38.8%47.1%
IFBench77.2%70.9%

Visual Benchmark Comparison

IBM Granite 4.2 30B
Nemotron 3.5 Super VL (120B A12B)
Terminal-Bench 2.10.3 vs 0.7
0.3
0.7
SWE-bench Multilingual0.4 vs 0.7
0.4
0.7
GPQA0.7 vs 0.9
0.7
0.9
SWE-Bench Pro0.3 vs 0.5
0.3
0.5
SWE-Bench Verified0.6 vs 0.7
0.6
0.7
LiveCodeBench v60.8 vs 0.9
0.8
0.9
SciCode0.4 vs 0.5
0.4
0.5
IFBench0.8 vs 0.7
0.8
0.7

Verdict

Nemotron 3.5 Super VL (120B A12B) leads in 1 out of 3 comparison categories.

Overall Performance

Both models show comparable average scores: IBM Granite 4.2 30B — 0.6, Nemotron 3.5 Super VL (120B A12B) — 0.6.

Programming

On SWE-Bench, both models are nearly equal: IBM Granite 4.2 30B — 0.6, Nemotron 3.5 Super VL (120B A12B) — 0.7.

Recency

Nemotron 3.5 Super VL (120B A12B) is newer: released 10/15/2026 vs 8/25/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — IBM Granite 4.2 30B or Nemotron 3.5 Super VL (120B A12B)?
On the SWE-Bench benchmark, Nemotron 3.5 Super VL (120B A12B) shows a better result: 71.1% vs 57.0%.
Which model is cheaper — IBM Granite 4.2 30B or Nemotron 3.5 Super VL (120B A12B)?
API pricing data is available on the individual model pages.
Which has a larger context window — IBM Granite 4.2 30B or Nemotron 3.5 Super VL (120B A12B)?
Context window data is available on the individual model pages.

The IBM Granite 4.2 30B and Nemotron 3.5 Super VL (120B A12B) comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the IBM Granite 4.2 30B or Nemotron 3.5 Super VL (120B A12B) page. See also the complete list of AI model comparisons.