# Nemotron 3 SuperHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/nemotron-3-super-120b-a12b-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/nemotron-3-super-120b-a12b-high.

NVIDIA

Canonical URL: https://benchize.com/models/nemotron-3-super-120b-a12b-high
Last updated: Thu, 22 Oct 2026 04:40:22 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

NVIDIA

## Benchmarks

| Benchmark | Score | ± | Rank | Source |  |
| --- | --- | --- | --- | --- | --- |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 623.7 | Range 580.4–666.5 | 114 / 126 | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 623.7 \| rating \| reported \| Higher is better \| \| `overall` \| 61.32 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 57.17 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 61.4 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 57.4 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 72.57 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 57.32 \| source_score \| rubric \| Higher is better \| \| `slop` \| 64.52 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 71.88 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 66.68 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 53.55 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 61.16 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 60.27 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort high scoreScope 10_task_current sourceConfiguration nemotron-3-super-reasoning-or thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 580.4–666.5 interval [580.4,666.5] rank 121 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Nemotron 3 Super 120B (high) Evaluated 2026-10-08 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/120` |  |  |  |  |  |
| [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 47% | — | 71 / 191 | [bullshitbench · v2](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `green_rate` \| 0.47 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.35 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.0 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.1167 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort high suite v2 thinkingEnabled true ### Reported statistics acceptedCount 35 answeredCount 100 clearCount 47 errorCount 0 partialCount 18 rank 99 refusalCount 0 sampleSize 100 ### Source [Original source](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) Source bullshitbench Original model label nvidia/nemotron-3-super-120b-a12b Source version v2 Observed 2026-10-22T03:10:12.603Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/98` |  |  |  |  |  |

---
Cite as: Nemotron 3 SuperHigh — Benchize, https://benchize.com/models/nemotron-3-super-120b-a12b-high (retrieved 2026-10-22)