Codesota · Models · NVIDIA-Nemotron-3-Super-120B-A12B-BF166 results · 6 benchmarks
Model card

NVIDIA-Nemotron-3-Super-120B-A12B-BF16.

unknown
§ 02 · Benchmarks

Every benchmark NVIDIA-Nemotron-3-Super-120B-A12B-BF16 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01LiveCodeBenchComputer Code · Code Generationpass-181.2%#9/24source ↗
02Tau2-BenchAgentic AI · Tool Useaccuracy61.1%#11/11source ↗
03BrowseCompNatural Language Processing · Question Answeringaccuracy31.3%#14/16source ↗
04SWE-Bench VerifiedComputer Code · Code Generationaccuracy60.5%#19/22source ↗
05GPQA DiamondReasoning · Multi-step Reasoningaccuracy79.2%#32/74source ↗
06HLEReasoning · Multi-step Reasoningaccuracy18.3%#41/74source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where NVIDIA-Nemotron-3-Super-120B-A12B-BF16 actually performs.

Agentic AI
1
benchmark
avg rank #11.0
Computer Code
2
benchmarks
avg rank #14.0
Natural Language Processing
1
benchmark
avg rank #14.0
Reasoning
2
benchmarks
avg rank #36.5
§ 04 · Papers

1 paper with results for NVIDIA-Nemotron-3-Super-120B-A12B-BF16.

  1. 2025-12-24· 6 results

    NVIDIA Nemotron 3: Efficient and Open Intelligence

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
6
results
0 of 6 rows marked verified.