Models / Nemotron 3 Nano 30B A3B

NVIDIA

Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B 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 $0.10.

Results 16 Nov 2026 · 44 results · 5 sources

Test Nemotron 3 Nano 30B A3B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.06 in · $0.24 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
238 tokens a second; on its test prompt the answer starts after 8.9 s, thinking time included
Artificial Analysis, on its usual API, at thinking reasoning; 232–238 across 2 settings
Intelligence Index
8.9
Artificial Analysis, at thinking reasoning; 6.8–8.9 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
NVIDIA, based in the US
Weights published
Released
15 Dec 2025 (Artificial Analysis)
262,144 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 146th of 185Claude Opus 5.5 – $0.10 blended, 6th percentilecheapest: Mistral Nemo 10th of 65Nemotron 3.5 Super VL
Models priced under $0.25 per million tokens 19th of 41Claude Haiku 5.5 – sets this group 6th of 19Nemotron 3.5 Super VL
Models with similar intelligence sets this group – $0.10 blended, 10th percentilecheapest: gpt-oss-20b 4th of 16gpt-oss-20b
Models writing 200 or more tokens a second 12th of 14Muse Spark 1.3 – $0.10 blended, 23rd percentilecheapest: gpt-oss-20b sets this group
Models from developers based in the US 73rd of 92Claude Opus 5.5 – $0.10 blended, 8th percentilecheapest: Gemma 3 4B 8th of 33Nemotron 3.5 Super VL
Open-weights models 74th of 104MiMo-V2.6-Pro – $0.10 blended, 9th percentilecheapest: Mistral Nemo 6th of 43Nemotron 3.5 Super VL

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 147th of 159 available · 30th of 37 at its price
BenchmarkNemotron 3 Nano 30B A3BRank among availableBest available
OpenHands IndexOpenHands Index: average · reported 15.5% 31st 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 6.7% 93rd of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 6.0% 86th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
  • 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 131st of 187 available · 15th of 41 at its price
BenchmarkNemotron 3 Nano 30B A3BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 8.9 146th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 11.4% 123rd of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 75.7% 107th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 153rd of 169 available · 29th of 39 at its price
BenchmarkNemotron 3 Nano 30B A3BRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,314 135th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 25.9 113th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 111th of 139 available · 20th of 30 at its price
BenchmarkNemotron 3 Nano 30B A3BRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 9.6% 38th of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,362 108th of 109 Gemini 4 Argon 1,511
  • 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 Nano 30B A3B at $0.10 blended, Intelligence Index 8.9. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $0.10 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
NebiusFP8$0.06$0.24$0.10

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 Nano 30B A3BClaude 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 $0.10 $0.20$0.06$8.00$0.54
Tokens a second 238 2402779643
Intelligence Index 8.9 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 147th of 159 28th130th3rd23rd
Professional work – ––3rd–
Reasoning and knowledge 131st of 187 25th132nd1st13th
Writing 153rd of 169 –155th5th23rd
Sticking to the facts 111th of 139 ––3rd10th
Speed under pressure – 21st–––

Shaded figures are better than Nemotron 3 Nano 30B A3B's. A dash means no result.

Where it has been measured

19th 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, writing, and sticking to the facts.

Every result

44 published results from 5 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 1,362
1,357–1,367
174 of 182 Nemotron 3 Nano 30B A3B 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,317
1,306–1,328
249 of 406 Nemotron 3 Nano 30B A3B 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,242
1,229–1,255
299 of 411 Nemotron 3 Nano 30B A3B 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,331
1,312–1,350
233 of 363 Nemotron 3 Nano 30B A3B 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,291
1,282–1,300
273 of 413 Nemotron 3 Nano 30B A3B 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,314
1,308–1,319
268 of 413 Nemotron 3 Nano 30B A3B 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,267
1,256–1,277
296 of 412 Nemotron 3 Nano 30B A3B 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 · 23 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 14.4 167 of 187 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 6.8 379 of 413 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 8.9 340 of 413 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 39.9% 348 of 360 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 75.7% 213 of 360 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 4.6% 356 of 419 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 11.4% 264 of 419 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 37.5% 225 of 288 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 71.1% 56 of 288 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 10.7% 381 of 407 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 38.0% 321 of 407 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 232 16 of 137 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 238 13 of 137 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 30.6% 193 of 205 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 6.7% 163 of 188 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 12.1% 190 of 282 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 13.6% 182 of 282 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 0.36 1 of 137 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 8.85 56 of 137 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 6.0% 148 of 175 Nemotron 3 Nano 30B A3B (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 25.4% 233 of 286 Nemotron 3 Nano 30B A3B (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 40.9% 180 of 286 Nemotron 3 Nano 30B A3B (thinking reasoning) 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 15.5% 34 of 34 Nemotron 3 Nano 30B A3B (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 20.9% 32 of 34 Nemotron 3 Nano 30B A3B (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 6.2% 33 of 34 Nemotron 3 Nano 30B A3B (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 8.5% 34 of 34 Nemotron 3 Nano 30B A3B (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 34.2% 34 of 34 Nemotron 3 Nano 30B A3B (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 7.6% 34 of 34 Nemotron 3 Nano 30B A3B (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.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 35.0% 286 of 379 Nemotron 3 Nano 30B A3B 16 Dec 2025
UGI: requested-length error% off the requested word count, lower is better 251.0% 378 of 379 Nemotron 3 Nano 30B A3B (think-prefill reasoning) 18 Dec 2025
UGI: style adherencescore from 0 to 1, higher is better 0.28 364 of 379 Nemotron 3 Nano 30B A3B 16 Dec 2025
UGI: style adherencescore from 0 to 1, higher is better 0.25 379 of 379 Nemotron 3 Nano 30B A3B (think-prefill reasoning) 18 Dec 2025
UGI: writing scorescore out of 100, higher is better 25.9 306 of 379 Nemotron 3 Nano 30B A3B 16 Dec 2025
UGI: writing scorescore out of 100, higher is better 3.4 379 of 379 Nemotron 3 Nano 30B A3B (think-prefill reasoning) 18 Dec 2025

Not shown: Not other format limits such as character counts or bullet counts.

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.6% 48 of 108 Nemotron 3 Nano 30B A3B 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 9.6% 55 of 108 Nemotron 3 Nano 30B A3B 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Will Nemotron 3 Nano 30B A3B 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.