Models / Nemotron 3 Super 120B A12B

NVIDIA

Nemotron 3 Super 120B A12B

Nemotron 3 Super 120B A12B trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.17.

Results 16 Nov 2026 · 25 results · 3 sources

Test Nemotron 3 Super 120B A12B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.08 in · $0.45 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
12.8
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
NVIDIA, based in the US
Weights published
Released
11 Mar 2026
1,048,576 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 122nd of 185Claude Opus 5.5 – $0.17 blended, 15th percentilecheapest: Mistral Nemo –
Models priced under $0.25 per million tokens 14th of 41Claude Haiku 5.5 – sets this group –
Models with similar intelligence sets this group – $0.17 blended, 22nd percentilecheapest: gpt-oss-20b –
Models from developers based in the US 66th of 92Claude Opus 5.5 – $0.17 blended, 16th percentilecheapest: Gemma 3 4B –
Open-weights models 55th of 104MiMo-V2.6-Pro – $0.17 blended, 23rd percentilecheapest: Mistral Nemo –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 122nd of 159 available · 18th of 37 at its price
BenchmarkNemotron 3 Super 120B A12BRank among availableBest available
OpenHands IndexOpenHands Index: average · reported 36.2% 29th of 31 Claude Fable 5 81.0%
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 38.6% 72nd of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 10.3% 70th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 112th of 187 available · 11th of 41 at its price
BenchmarkNemotron 3 Super 120B A12BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 12.8 122nd of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 20.8% 101st of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 80.0% 94th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 125th of 169 available · 14th of 39 at its price
BenchmarkNemotron 3 Super 120B A12BRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,360 114th of 153 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 132nd of 139 available · 25th of 30 at its price
BenchmarkNemotron 3 Super 120B A12BRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,390 101st of 109 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Nemotron 3 Super 120B A12B at $0.17 blended, Intelligence Index 12.8. "Similar intelligence" means within 4 points or better.

Where to run it

3 hosts on OpenRouter at the standard service tier, with a median of $0.17 blended per million tokens; quantisation where the host states it: BF16, FP8. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraBF16$0.07$0.40$0.16
DekaLLMFP8$0.08$0.45$0.17
CrusoeFP8$0.30$2.40$0.82

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Nemotron 3 Super 120B A12BClaude Haiku 5.5
most intelligent at under $0.25 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent with open weights
Price per million tokens $0.17 $0.20$0.06$8.00$0.54
Tokens a second – 2402779643
Intelligence Index 12.8 43.410.057.646.3
Spring Prompt overall – 40–82–
Rank among available models, by use case
Product listings – 20th–13th–
Decks from an analysis – 18th–7th–
User surveys – 7th–4th–
Marketing planning – 30th–9th–
Agents and tool use 122nd of 159 28th130th3rd23rd
Professional work – ––3rd–
Reasoning and knowledge 112th of 187 25th132nd1st13th
Writing 125th of 169 –155th5th23rd
Sticking to the facts 132nd of 139 ––3rd10th
Speed under pressure – 21st–––

Shaded figures are better than Nemotron 3 Super 120B A12B's. A dash means no result.

Where it has been measured

14th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for agents and tool use, and sticking to the facts.

Artificial Analysis lists it but has not published a speed for it yet

Every result

25 published results from 3 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,390
1,383–1,397
159 of 182 Nemotron 3 Super 120B A12B 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,350
1,335–1,365
215 of 406 Nemotron 3 Super 120B A12B 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,303
1,286–1,321
231 of 411 Nemotron 3 Super 120B A12B 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,393
1,370–1,415
188 of 363 Nemotron 3 Super 120B A12B 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,342
1,330–1,355
212 of 413 Nemotron 3 Super 120B A12B 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,360
1,353–1,368
203 of 413 Nemotron 3 Super 120B A12B 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,324
1,311–1,338
221 of 412 Nemotron 3 Super 120B A12B 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 12 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 37.7 125 of 187 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 12.8 281 of 413 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 80.0% 174 of 360 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 20.8% 197 of 419 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 71.5% 49 of 288 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 65.7% 227 of 407 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 36.2% 179 of 205 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 38.6% 126 of 188 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 28.8% 112 of 282 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 10.3% 122 of 175 Nemotron 3 Super 120B A12B 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 67.8% 134 of 286 Nemotron 3 Super 120B A12B 20 Oct 2026

Not shown: Not your codebase or tools.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 36.2% 31 of 34 Nemotron 3 Super 120B A12B (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 20.6% 33 of 34 Nemotron 3 Super 120B A12B (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 12.5% 25 of 34 Nemotron 3 Super 120B A12B (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 40.0% 28 of 34 Nemotron 3 Super 120B A12B (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 62.0% 31 of 34 Nemotron 3 Super 120B A12B (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 45.7% 29 of 34 Nemotron 3 Super 120B A12B (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Will Nemotron 3 Super 120B A12B work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.