priorsBuilder

NVIDIA · released 2026-08-11

Nemotron 3.5 Lightning

Measured on 38 benchmarks.

General frontier

19.2

#111 of 136 models

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #305default of 58710.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #228default of 526-17.7

Leader: Opus 5.5 · 46.4

All 38 benchmarks

show 36 more

agentic

AA-Briefcase v1.1

224 results
  1. #173default of 224506

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #194default of 2190.8%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #50default of 5018.4%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #79default of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #75default of 782.9%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #68default of 692.6%

Leader: Fable 5.1 · 49.2%

agentic

τ³-Banking

206 results
  1. #155default of 2068.9%

Leader: Qwen 3.8 Max · 51.3%

coding

Code Migration

77 results
  1. #74default of 773.0%

Leader: Sonnet 5.5 · 69.8%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #54default of 620.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #39default of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #56default of 6218.2%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #201default of 22632.1%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #80default of 8552.8%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #74default of 7410.9%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench v2.1-AA

238 results
  1. #169default of 23824.3%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #146default of 2160.5%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #103default of 1050.0%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #314default of 61012.9

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #38default of 177$0.09

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #24default of 177$105

Leader: GPT-6 Luna · $10.63

economics

CorpFin (Vals)

117 results
  1. #88default of 11754.2%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #70default of 7417.0%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #76default of 7818.5%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #176default of 2103.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #200default of 288638

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #412default of 52614.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #66default of 52662.4%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

GPQA Diamond

539 results
  1. #255default of 53974.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MedScribe

96 results
  1. #96default of 964.3%

Leader: Opus 5.5 · 91.4%

long-context

AA-LCR v1.1

523 results
  1. #270default of 52360.3%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #87default of 941.1%

Leader: Sonnet 5.5 · 75.0%

math

ProofBench v1.1

52 results
  1. #52default of 520.0%

Leader: Sonnet 5.5 · 100.0%

reasoning

CritPt

529 results
  1. #345default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

safety

CyberBench v1.1

45 results
  1. #44default of 4529.5%

Leader: Wonder · 80.4%

speed

Latency (Time to First Token)

351 results
  1. #14default of 3510.6s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #14default of 351300.0

Leader: Celeris-1 · 1522.5