Which is better, Nemotron 3 Super 120B A12B or Qwen3.5 4B?

Nemotron 3 Super 120B A12B vs Qwen3.5 4B

26 SHARED BENCHMARKS

Across 26 shared benchmarks, Nemotron 3 Super 120B A12B scores higher on 19 and Qwen3.5 4B on 7. The widest gap is AA Agentic Index, where Qwen3.5 4B scores 36.3 against 4.1. Qwen3.5 4B is the cheaper of the two on tracked API pricing ($0.03 against $0.19 per million input tokens).

NVIDIAVSALIBABA26 SHARED19–7 HEAD-TO-HEAD

BenchmarkNemotron 3 Super 120B A12BMARGINQwen3.5 4B

AA Agentic Index4.136.3

AA Intelligence13.620

AA-LCR65.763

AA-Omniscience-41.5-58.4

aime_202691.799

AIME25 no tools92.254.3

Artificial Analysis Coding Index37.722.6

critpt3.10

gdpval7.28.3

GPQA Diamond82.777.1

HLE22.89.9

HMMT 202594.776.8

hmmt_feb_202685.284.1

IFBench72.659.2

mmlu_prox79.471.5

MMLU-Pro83.879.1

multichallenge55.249

OmniScience Accuracy24.315.1

OmniScience Non-Hallucination1313.4

scicode4218.3

TauBench V3 - Banking10.36.8

Terminal-Bench 2.138.625.8

Terminal-Bench Hard28.818.2

τ²-Bench (Retail)62.871.9

τ²-Bench Telecom (AA run)67.892.1

τ³-Bench10.18.2

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, direct), otherwise the lowest tracked offer.

Compare Nemotron 3 Super 120B A12B withALL PAIRINGS →

Across the fieldGemini 3.6 Flash GPT-5.5 Claude Opus 4.8 GPT-4o GPT-5.6 Sol Gemini 3.1 Pro GPT-5.4 GPT-5.2

Compare Qwen3.5 4B withALL PAIRINGS →

AlibabaQwen3.5 35B A3B Qwen3 VL 4B (Reasoning)Qwen3.5 397B A17B Qwen2.5 Instruct 72B Qwen3.5 27B Qwen3.6 Plus

Across the fieldGPT-5.5 Claude Opus 4.8 GPT-4o GPT-5.6 Sol Gemini 3.1 Pro GPT-5.4 GPT-5.2 Claude Opus 4.6